chore: prepare release v0.34.0

Assisted-by: DeepSeek V4.1 Flash

.gitea/workflows/release.yml

@@ -5,9 +5,9 @@
 # even at its own <module>/vX.Y.Z tag and this workflow's smoke test can never pass for
 # it. A Go repository is one module at the root.
 #
-# The version contract these steps implement is in the `release` skill, and its point is
-# that nothing is injected: the toolchain records the tag into the binary's build
-# information, so the build simply has to happen at the tag, which the trigger guarantees.
+# The version contract these steps implement: nothing is injected.  The toolchain records
+# the tag into the binary's build information, so the build simply has to happen at the
+# tag, which the trigger guarantees.
 #
 # The gates run in their own job, once, before the matrix, minus the race detector: race
 # never runs on a push path or a tag, and the local gate raced this tree before the tag
@@ -55,6 +55,25 @@ jobs:
             print qq{tag $v\n};
           '
 
+      - name: Security policy names this release
+        # The supported-versions table is the one part of SECURITY.md that
+        # carries a version, so it goes stale the moment a tag is cut.  Fail
+        # here rather than publish a policy naming the previous release.
+        env:
+          VERSION: ${{ gitea.ref_name }}
+        run: |
+          perl -e '
+            my $v = $ENV{VERSION} // q{};
+            (my $nv = $v) =~ s/^v//;
+            open(my $f, q{<}, q{SECURITY.md}) or die qq{SECURITY.md: $!\n};
+            local $/;
+            my $t = <$f>;
+            close $f;
+            $t =~ m{^\|\s*\Q$nv\E\s*\|\s*yes\s*\|}m
+              or die qq{ERROR: SECURITY.md does not name $nv as supported; update the table before releasing.\n};
+            print qq{SECURITY.md names $nv\n};
+          '
+
       - name: Build
         run: go build ./...
 
@@ -78,6 +97,11 @@ jobs:
         # The same command as in test.yml, so the floor is the same number everywhere.
         run: go test -count=1 -timeout 10m -coverprofile=coverage.out ./arch/... ./asm/... ./ast/... ./disasm/... ./format/... ./lexer/... ./lint/... ./lsp/... ./parser/... ./token/... ./verify/...
 
+      - name: Tests outside the coverage set
+        # The same command as in test.yml: the CLI's exit codes and manual-page guard,
+        # and the debugger's architecture-neutral units, run outside the floor.
+        run: go test -count=1 -timeout 10m ./cmd/... ./debug/...
+
       - name: Coverage floor
         run: |
           perl -e '

.gitea/workflows/test.yml

@@ -84,6 +84,14 @@ jobs:
         # suites); the runner's Go setup provides both the tool and GOROOT.
         run: go test -count=1 -timeout 10m -coverprofile=coverage.out ./arch/... ./asm/... ./ast/... ./disasm/... ./format/... ./lexer/... ./lint/... ./lsp/... ./parser/... ./token/... ./verify/...
 
+      - name: Tests outside the coverage set
+        # The CLI and the debugger sit outside `packages` because a thin main and a
+        # ptrace-bound package pull the total under the floor, but their tests guard
+        # shipped surfaces: the command exit codes, the manual pages against the
+        # binary's own help, and the debugger's architecture-neutral units.  They run
+        # here so the floor stays a product measure and nothing is left untested.
+        run: go test -count=1 -timeout 10m ./cmd/... ./debug/...
+
       - name: Oracle parity
         # Re-run the live go-tool-asm comparison as its own step so that a parity
         # regression names the gate that failed instead of hiding inside the suite.

CHANGELOG.md

@@ -9,6 +9,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+-
+
+## [0.34.0] - 2026-09-20
+
+### Added
+
 - **Indirect JMP and CALL on all four architectures.**  `JMP AX`,
   `CALL AX`, `JMP (BX)` and the memory forms encode at byte parity with
   the toolchain (FF /2 and FF /4 on amd64); arm64 lowers `JMP (R0)` to
@@ -16,8 +22,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   JALR; loong64 accepts the raw `JIRL rd, rj, off` spelling the Go
   assembler cannot express.  A frameless amd64 function containing a
   CALL now receives the toolchain's forced base-pointer frame.  The
-  verify trampolines join the ground-truth lists, and a lint check for
-  control flow through registers and memory extends to the new forms.
+  riscv64 and loong64 verify trampolines join their ground-truth lists,
+  and a lint check for control flow through registers and memory extends
+  to the new forms.
 - **`gasm asm -GOARCH` and `gasm diff -GOARCH`.**  The target
   architecture can be named explicitly instead of inferred from the
   file-name suffix, which is how the suffix-less majority of GOROOT's
@@ -25,38 +32,40 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **`gasm audit-instructions --corpus [dir]`.**  Assembles every `.s`
   file under a directory (default GOROOT/src) with the gasm encoder
   only: suffixed files for their architecture, suffix-less files for
-  all four, as a GOARCH build would.  Reports the headline number (108
-  of 627 GOROOT files, 17.2 %, assemble for every target architecture,
-  against 23 in the previous release), the per-architecture pass rates
-  and the most common failure reasons with a representative file each,
+  all four, as a GOARCH build would.  Reports the headline number (127
+  of 627 GOROOT files, 20.3 %, assemble for every target architecture),
+  the per-architecture pass rates and the most common failure reasons
+  with a representative file each,
   which drive the encodability backlog by frequency.
-- **Fuzz targets for the parser and the formatter.**  FuzzParse (no
-  panic, always a usable file) and FuzzFormatIdempotency (formatting
-  twice equals formatting once; clean input stays clean) seed
-  themselves from the repository's kernels, so the plain test suite
-  replays every seed in CI and `just fuzz` runs the mutation engine on
-  demand.
-- **Oracle parity as its own CI step.**  The push pipeline already ran
-  the live go-tool-asm comparison inside the suite; a dedicated step
-  now names that gate when it fails.
-- **Man pages.**  docs/man carries gasm(1) and one page per command,
-  written in roff: synopsis, description, every flag with its default,
-  exit status, worked examples and cross-references.
+- **The parser and the formatter are fuzzed.**  Two targets carry the
+  guarantee: no input makes the parser panic, and every input yields a
+  file the rest of the toolkit can work on; formatting twice equals
+  formatting once, and clean input stays clean.  They seed from the
+  repository's own kernels, and `just fuzz` drives the mutation engine
+  on demand.
+- **Man pages.**  docs/man carries gasm(1) and a page for every command
+  except `version`, which gasm(1) documents itself, written in roff:
+  synopsis, description, every flag with its default, exit status,
+  worked examples and cross-references.
   `just install-man` compresses them into ~/.local/share/man (MANDIR
   overrides) and `just uninstall-man` removes them.  A test builds the
-  binary and compares every command's `-h` output with its page, so the
-  pages cannot drift from the CLI.
+  binary and compares each page's flags and synopsis with its own `-h`
+  output, so the pages cannot drift from the CLI.
 
 ### Changed
 
+- **Go 1.27.1 required.**  The module declares `go 1.27.1`, so building
+  from source needs that patch release or newer.
 - **Canonical just recipes.**  `just gates` is the definition of done
   (build, fmt-check, vet, test, race).  `install` now builds and copies
   the binary into `~/.local/bin` (`BINDIR` overrides) instead of
   downloading module dependencies, and `install-bin` is gone.  The test
-  gate sweeps the logic packages (arch through verify; the hardware-bound
-  `debug` and the thin `cmd/gasm` sit outside it), so the coverage floor
-  is computed over the product code and the number is identical locally
-  and in CI.  `fuzz` requires its target package.
+  gate sweeps the logic packages (arch through verify; the ptrace-bound
+  `debug` and the thin `cmd/gasm` sit outside the coverage profile), so
+  the coverage floor is computed over the product code and the number is
+  identical locally and in CI; the two excluded packages' own tests run
+  in the gate and in the pipelines, outside the floor.  `fuzz` requires
+  its target package.
 - **The reported version comes from the build.**  `gasm --version`
   prints the version the toolchain recorded: the tag on a tagged
   checkout, a pseudo-version naming the commit below one, `+dirty` on a
@@ -78,8 +87,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   synopsis, the commands, every flag with its default, the exit codes and
   worked examples; `CONTRIBUTING.md` carries the Contributor terms and
   states the commit trailer form, the one-logical-change rule and the
-  licence header rule.  The repository's own assembly (the `verify`
-  trampolines and the test kernels) is in `gasm fmt` canonical form.
+  licence header rule; `SECURITY.md` states how a vulnerability is
+  reported and what to expect.  The repository's own assembly (the
+  `verify` trampolines and the test kernels) is in `gasm fmt` canonical
+  form.
 - **The README states the project's purpose and status.**  It opens with
   a warning that the tool is an experiment under active development,
   version 0.x.x, free to change without warning, with 1.0.0 far off,
@@ -88,7 +99,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   Go toolchain), argues the case for the syntax in a new Why Plan 9
   assembly section, and carries a Direction section: extended
   instruction support, full GOOBJ and ELF compilation, Linux and
-  FreeBSD, and the four architectures.
+  FreeBSD, and the four architectures.  A Validation status section
+  states what has been executed where: amd64 on real hardware, the other
+  three architectures under qemu-user emulation, the encoding parity on
+  the host for all four, and the debugger's ptrace path on amd64 only.
 
 ### Fixed
 
@@ -109,6 +123,199 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   lines entered the alignment width computation, and rendered `/ *`,
   `> >` sequences re-lexed as comments and shifts.  The label, width and
   spacing rules now agree between passes.
+- **`gasm fmt` deleted the `|` separators from TEXT and GLOBL flag
+  lists.**  The lexer had no token for `|`, the formatter dropped the
+  resulting illegal token, and an in-place format silently rewrote
+  `NOSPLIT|DUPOK` as `NOSPLIT DUPOK`, which the Go assembler rejects.
+  The bars now round-trip byte-identically, and `·foo<ABIInternal>(SB)`
+  parses its ABI marker instead of swallowing `ABIInternal` and `SB`
+  into the flags, which produced false lint warnings on the standard
+  runtime spelling.
+- **A malformed TEXT declaration crashed `gasm lint` and the language
+  server.**  A TEXT line without a symbol left a nil name that lint and
+  the LSP dereferenced; both now carry on with a diagnostic.  A branch
+  to a label at the end of a function body panicked the liveness
+  analysis the same way.  A real NUL byte truncated the token stream
+  (everything after it was dropped); it is an illegal token now, invalid
+  UTF-8 no longer inflates byte offsets, and CRLF files format to
+  uniform LF.
+- **The class-2 stack guard branched four bytes past its target.**  When
+  the underflow branch relaxed to its 32-bit form, its displacement was
+  still computed as if the branch were two bytes long, so it landed
+  inside the morestack CALL instead of the compare that decides it.
+  The long form is reachable once a large frame carries a body of roughly
+  a hundred bytes.
+- **Immediate operands wrapped silently on amd64.**  Shift counts,
+  immediates beyond the operand's width and displacements beyond int32
+  truncated without a diagnostic (`SHLQ $300` assembled as `$44`); they
+  are range-checked now, matching `go tool asm`.  EVEX scalar moves
+  (`VMOVSS Z1, Z2`) accepted forms the toolchain rejects and emitted
+  invalid encodings; `PUSHW`/`POPW` emit the 0x66-prefixed forms the
+  toolchain emits; `PUSHL` is rejected as illegal in 64-bit mode; a bare
+  zero-operand `JE` reports a diagnostic instead of panicking.
+- **The arm64 shift and divide instructions encoded entirely different
+  operations.**  `LSL`, `LSR`, `ASR` and `ROR`, immediate and register
+  forms, all encoded as `ORR`; `SDIV`/`UDIV` sat in the wrong opcode
+  space; `MADD`/`MSUB` never encoded the accumulate operand and silently
+  read X0 for it.  All now match the toolchain byte for byte (new
+  differential kernels cover shifts, divides and multiplies), MADD
+  takes its four operands in the toolchain's order, and shift amounts at
+  or above the operand width are rejected.
+- **arm64 multi-chunk immediates corrupted every branch that followed
+  them.**  The size pass and the emitter disagreed on the expansion of
+  constants with three or more non-zero 16-bit chunks and of `MOVW $-1`,
+  so later label displacements were computed against the wrong offsets.
+  The size now comes from the encoder itself.  Large-frame stack guards
+  (frames from roughly 64 KiB) branched to the wrong morestack entry,
+  and the pcsp and DWARF CFA boundaries for materialised large frames
+  are computed from the real prologue word counts.
+- **arm64 immediates and addressing wrapped instead of erroring.**
+  Constants beyond the encodable range (`ADD $0x100000000`) wrapped to
+  zero, memory offsets wrapped at 2^31, exclusive and atomic accesses
+  silently ignored their offsets (`LDXR 8(R1)` read `[R1]`), and large
+  register-based offsets were routed through SP instead of the operand's
+  base.  All four now either encode correctly or produce diagnostics.
+- **riscv64 compressed stores with certain offsets wrote to the wrong
+  address.**  The C.SD/C.SW/C.FSD immediate pattern dropped one bit, so
+  any register-relative store with offset bit 4 or 5 set targeted a
+  different address than the same-index load beside it.  `FENCE`
+  assembled as `fence 0,0` instead of `fence iorw, iorw`.  Branch and
+  jump displacements beyond ±4 KiB / ±1 MiB wrapped silently; they are
+  diagnostics now.  The GOROOT width spellings (`MOVW 4(SP), X9`)
+  compress to their C.LW/C.SW forms exactly as the toolchain lowers
+  them, restoring byte parity for those shapes.
+- **loong64 `MOVW $c, Fd` wrote a general register.**  The immediate was
+  routed to the GPR of the F register's number (`MOVW $2, F4` clobbered
+  argument register R4), and the correct R30 + `movgr2fr.w` sequence was
+  unreachable.  Two-operand `BLTU R4, label` encoded as `beqz`
+  (sometimes-taken where the toolchain's form is never-taken), and
+  out-of-range FP constants and BSTRINS/BSTRPICK bit numbers wrapped
+  silently; all are corrected or diagnosed.
+- **ELF objects carried wrong relocation records.**  The amd64
+  stack-guard TLS load relocated as R_X86_64_PC32 against the null
+  symbol (every non-NOSPLIT object mislinked); arm64 SB references
+  applied HI21 twice instead of the HI21/LO12 pair; riscv64 PCREL_LO12
+  referenced the target instead of its AUIPC site, which the system
+  linker rejects; riscv64 and loong64 e_flags declared the soft-float
+  ABI, so standard linkers refused the merge.
+- **ELF DWARF was unparseable.**  Eight abbrev-table constants were
+  wrong, the version-5 line header carried DWARF2-shaped tables, the
+  section count omitted `.debug_frame` (it sat past the section table,
+  invisible to every tool), the CIE hardcoded one architecture's
+  CFA and return-address registers for all four, and no DWARF address
+  was ever relocated: the `.rela.debug_info` and `.rela.debug_line`
+  records were computed and then discarded, so every address stayed
+  zero after linking.  The tables parse in readelf, the registers are
+  per-architecture, `.rela.debug_info`, `.rela.debug_line` and
+  `.rela.debug_frame` are emitted, and addresses resolve after the
+  link; a data-only file emits a valid object instead of panicking, and
+  the DWARF records the real source path.
+- **GOOBJ cross-package references resolved against the wrong object.**
+  External package indices were zero-based against a table that
+  reserves zero for the dummy invalid package, and symbol indices
+  ignored the hashed definition blocks between the sections, so a
+  reference into the first external package could bind to whatever
+  object the loader saw first.  An end-to-end cross-package link pins
+  the chain.  arm64 ADRP pairs now emit the toolchain's single 8-byte
+  relocation (the previous twin 4-byte records were a hard link error),
+  and symbols no longer claim the linkname flag the toolchain reserves
+  for `//go:linkname` declarations.
+- **The arm64 JIT trampolines saved a scratch register as the stack
+  pointer.**  `enterJIT` and its checked twin stored R3, a plain
+  caller-saved register on arm64, and restored RSP from it, so the
+  first JIT call would have returned to a garbage stack.  The loong64
+  trampoline hands its leave address through the raw-symbol pattern the
+  arm64 one uses, avoiding the ABI wrapper's prologue.
+- **The checked-ABI report flagged legal frames.**  The red-zone canary
+  sat 64 bytes below the entry stack, so any kernel with a larger
+  declared frame reported "stack below SP written"; the guard now sizes
+  itself from the kernel's frame.  The amd64 JIT tests are gated to
+  amd64 hosts (the suite previously SIGILL-crashed on the other three
+  architectures), fuzz signatures wider than the TEXT frame report
+  instead of panicking, `--buf` specifications are validated strictly
+  (a typo no longer verifies against a zeroed buffer), and ABI0
+  parameter sizes cover `string` and `complex` correctly.
+- **amd64 hardware watchpoints never armed.**  The debug registers were
+  poked at offsets inside `user_regs_struct`, corrupting five general
+  registers while the REPL reported success; they now use the real
+  u_debugreg window and stop on the watched address.  loong64 watch
+  goes through the kernel's HW_WATCH regset (riscv64 reports the
+  kernel's interface as unsupported instead of failing obscurely).
+- **`gasm debug` hung on the first faulting kernel.**  Genuine
+  SIGSEGV/SIGBUS/SIGFPE/SIGILL stops were discarded as runtime noise
+  and the faulting instruction restarted forever; faults now surface as
+  reported stops.  Conditional breakpoints with a false condition
+  resumed mid-instruction, `next` and `finish` evaluated traps with
+  stale registers and landed off instruction boundaries, and the
+  breakpoint restore covered one byte of the four-byte traps (arm64
+  silently skipped the instruction under it); the trap PCs follow the
+  kernel's reporting on every architecture.  `regs` reports YMM from
+  the xstate (a struct-size overrun crashed FP register reads before),
+  V register halves print correctly on arm64, `unwatch` accepts the
+  architecture's slot range, `x <addr> -8` no longer crashes, break
+  conditions accept memory operands, and session scratch directories
+  are cleaned up.
+- **The language server died on one malformed frame and corrupted
+  sources on rename.**  A bad `Content-Length` or an unparsable JSON
+  body terminated the process instead of answering `-32700` and
+  continuing; rename and references covered the stripped name instead
+  of the full `·name` token, so renaming produced `·helper` minus its
+  last letter; documentHighlight never matched middle-dot symbols.
+  Positions are UTF-16 code units in both directions (astral characters
+  no longer shift columns) and responses always carry an explicit
+  `result` member.
+- **The linter now recognises the `g` spelling of the goroutine
+  register.**  `MOVD R0, g` clobbered R28 on arm64 (and the equivalents
+  on the other architectures) unflagged, and the numeric spellings the
+  linter did track are rejected by the toolchain there, so `g` was the
+  one spelling that escaped the audit.  FUNCDATA and PCDATA literal
+  indices are validated against the ranges the runtime defines.
+- **Usage errors exit 2 uniformly.**  `audit-instructions` and
+  `scaffold` argument errors and an unknown `asm --format` exited 1 (or,
+  for `--format` without `-o`, exited 0 silently); the documented
+  exit-2 contract now holds, `asm -o` no longer prints the hex dump it
+  claimed to replace, and `verify --ground-truth` works for amd64
+  kernels on non-amd64 hosts instead of refusing with JIT advice.
+- **arm64 store-exclusive instructions read their operands in the
+  toolchain's order.**  `STXR` treated the first register as the status
+  register where `go tool asm` reads it as the data register, so the
+  same source assembled to different code in the two assemblers; the
+  pair forms (`STXP`, `LDXP` and their acquire/release variants) are
+  accepted now, in the toolchain spelling.
+- **Large arm64 frames matched the toolchain's sequences.**  A frame
+  beyond the immediate range that is not a movcon constant (roughly
+  64 KiB and up) made `gasm verify` report a false mismatch: the
+  toolchain splits the prologue subtraction into two 12-bit immediates
+  and materialises the non-leaf epilogue addition through the temporary
+  register; gasm emits the same sequences and the spadj boundaries
+  follow the real word counts.
+- **The width spellings GOROOT uses assemble.**  `MOVLQZX` (four uses in
+  `runtime/asm_amd64.s`), `MOVBQSX`, `MOVWQSX`, `MOVBLSX`, `MOVBWSX`,
+  `MOVBWZX` and `PMOVMSKB` (the bytealg kernels) encode byte-identically
+  with `go tool asm`, and the linter reports them encodable; a
+  `MOVLQZX` is the plain 32-bit move, exactly as the toolchain lowers
+  it.
+- **`verify --ground-truth` no longer reports a mismatch for functions
+  whose size is not a multiple of 16.**  The toolchain pads text symbols
+  to 16-byte boundaries; the comparison now checks the padding is zero
+  instead of comparing it, the same rule the test suite applies.
+- **riscv64 accepts the `g` spelling of the goroutine register**, like
+  the other architectures, and the abi kernels use it; every verify
+  kernel is now ground-truth checkable (the numeric `X27` spelling the
+  kernels used is one `go tool asm` rejects).
+- **Two more spellings GOROOT uses now assemble.**  riscv64 `FCLASSD`
+  (classify a float64 into an integer mask) is encodable, and a
+  displacement written as a product (`0*8(X5)`, the toolchain's own
+  spelling in several kernels) parses instead of being rejected.
+- **loong64 JIT execution enabled.**  The loong64 trampoline is now
+  validated end to end under qemu-user emulation (plain and ABI-checked
+  calls, goroutine-clobber detection), so `gasm verify` runs the JIT
+  checks on loong64 hosts instead of forcing every loong64 kernel down
+  the ground-truth path.  The arm64 and riscv64 trampolines carry the
+  same validation; the arm64 ABI test now seeds its kernel arguments
+  (a zeroed block made the passthrough check meaningless), and the
+  loong64 basic kernel's branch maze terminates on every path so the
+  smoke sweep cannot spin on leftover register values.
 
 ## [0.33.0] - 2026-09-14
 
@@ -327,7 +534,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [0.31.0] - 2026-08-20
 
-The arm64 encoder (Phase 5; complete) ships with ELF64 and GOOBJ emission,
+The arm64 encoder ships with ELF64 and GOOBJ emission,
 verified byte-for-byte against `GOARCH=arm64 go tool asm` and linked into a
 real `go build`.  The encoder covers the full integer instruction set, FP
 arithmetic, conditional select, CRC32, and the MOV pseudo-instruction with
@@ -335,7 +542,7 @@ bitmask immediate encoding.  The project now requires Go 1.27.
 
 ### Added
 
-- **arm64 encoder (Phase 5; complete).**  `gasm asm` can now assemble `_arm64.s`
+- **arm64 encoder.**  `gasm asm` can now assemble `_arm64.s`
   files: the AArch64 integer instruction set with the MOV pseudo-instruction and
   its immediate-constant expansions (MOVZ/MOVN/MOVK for wide immediates, ORR with
   logical bitmask encoding for values like `$1`), data-processing (shifted
@@ -343,8 +550,9 @@ bitmask immediate encoding.  The project now requires Go 1.27.
   immediate), conditional and unconditional branches, FP/SP frame mapping,
   SB/global symbol references (ADRP+ADD pairs with `R_ADDRARM64` relocations),
   jump chain folding, and ELF64 emission (`gasm asm --format elf`).  Ground-truth
-  verification against `GOARCH=arm64 go tool asm` matches byte-for-byte.  Phase 5
-  (the other architectures; RISC-V, LoongArch, arm64) is now complete.
+  verification against `GOARCH=arm64 go tool asm` matches byte-for-byte.  The
+  encoder set for the remaining architectures (RISC-V, LoongArch, arm64) is
+  complete.
 
 ### Changed
 
@@ -354,7 +562,7 @@ bitmask immediate encoding.  The project now requires Go 1.27.
 
 ## [0.30.0] - 2026-08-13
 
-The LoongArch encoder (Phase 5) ships with ELF64 and GOOBJ emission, verified
+The LoongArch encoder ships with ELF64 and GOOBJ emission, verified
 byte-for-byte against `GOARCH=loong64 go tool asm` and linked into a real
 `go build`; the shared GOOBJ emitter now writes the per-function DWARF symbols
 the linker's DWARF pass reads.  The RISC-V encoder reaches byte-for-byte parity
@@ -365,7 +573,7 @@ tracks four hardware watchpoint slots, and the toolkit is Linux-only.
 
 ### Added
 
-- **LoongArch encoder (Phase 5).**  `gasm asm` can now assemble `_loong64.s`
+- **LoongArch encoder.**  `gasm asm` can now assemble `_loong64.s`
   files: the full LoongArch64 instruction set with the dual-form arithmetic
   mnemonics, the 16/21-bit branch families, the MOV pseudo-instruction and
   its immediate-constant expansions, FP/SP frame mapping, SB/global symbol
@@ -454,7 +662,7 @@ tracks four hardware watchpoint slots, and the toolkit is Linux-only.
 
 - **Linux only.**  The toolkit, its CI and the released binaries are now
   Linux-only; cross-compiled to linux/{amd64,arm64,riscv64,loong64}.
-- **Phase 4 closed.**  README's "Remaining" list for the debugger is gone;
+- **Debugger complete.**  README's "Remaining" list for the debugger is gone;
   disassembly at PC, memory-write, watchpoints, and source-line mapping are
   all shipped.
 
@@ -664,7 +872,7 @@ exposes the full dynamic-analysis toolkit.
 
 ## [0.20.0] - 2026-07-25
 
-Coverage profiling: the third pillar of Phase 3.  Static basic-block
+Coverage profiling.  Static basic-block
 enumeration from the assembler's label map, combined with multi-input path
 diversity measurement; how many observationally distinct execution paths a
 test corpus exercises.
@@ -689,7 +897,7 @@ execute) without fighting the runtime.
 
 ## [0.19.0] - 2026-07-24
 
-Runtime ABI checks: the second pillar of Phase 3.  The JIT trampoline now
+Runtime ABI checks.  The JIT trampoline now
 has an ABI-checking variant that sets sentinels in the callee-saved registers
 (BP, R14) before entering the assembled function and verifies they survive on
 return, plus a red-zone canary (128 bytes below SP filled with 0xA5) that
@@ -724,7 +932,7 @@ codes.  This is the automated form of the project's bit-identical contract.
 
 ## [0.17.0] - 2026-07-22
 
-Phase 3 begins: dynamic analysis.  A JIT execution substrate that assembles
+Dynamic analysis.  A JIT execution substrate that assembles
 Plan 9 amd64 kernels into executable memory and calls them directly; pure Go
 (stdlib only, `syscall.Mmap` + an assembly trampoline), no cgo, no external
 toolchain.
@@ -1131,8 +1339,8 @@ support).
 
 ## [0.2.0] - 2026-07-07
 
-The Phase 2 assembler grows the SIMD set: shuffles, extract/insert, permute
-and the moves, on top of the Phase 1 VEX forms.
+The assembler grows the SIMD set: shuffles, extract/insert, permute
+and the moves, on top of the VEX forms of the first release.
 
 ### Added
 
@@ -1168,7 +1376,7 @@ and the moves, on top of the Phase 1 VEX forms.
 
 ## [0.1.0] - 2026-07-06
 
-Initial release; the Phase 1 foundation.
+Initial release: the foundation.
 
 ### Added
 

CONTRIBUTING.md

@@ -24,7 +24,9 @@ below; submitting one means you accept them.
 ## Development setup
 
 Requirements: Go 1.27.1, the exact version the `go` directive in `go.mod`
-declares, and [just](https://github.com/casey/just) for the recipes.
+declares, [just](https://github.com/casey/just) for the recipes, and a C
+compiler (gcc), because `just gates` includes `just race` and the race
+detector needs cgo.
 
 ```sh
 git clone https://sourcedock.dev/petrbalvin/gasm-devkit.git
@@ -54,15 +56,20 @@ workflow builds the assets and publishes the release and its notes.
 ## Code style
 
 `gofmt` and `go vet` run through `just fmt` and `just vet`, with zero diff and zero
-warnings tolerated. `just gates` is the definition of done in one command, and the recipe
-file names what it contains. Errors are checked explicitly, wrapped as
-`fmt.Errorf("context: %w", err)`, and nothing panics outside `main`. The `golang`
-skill holds the rules the project follows; the recipe file holds the commands.
+warnings tolerated. `just vet` is two gates, `go vet ./...` and `go fix -diff ./...`,
+so the modernisation rewrites are enforced too. `just gates` is the definition of done in
+one command, and the recipe file names what it contains. Errors are checked explicitly,
+wrapped as `fmt.Errorf("context: %w", err)`, and nothing panics outside `main`. The
+recipe file holds the commands, and the language and standard-library surface is the one
+the `go` directive in `go.mod` pins.
 
 - `golang.org/x/arch` is the one module dependency, and it is linked into the binary:
   `gasm dis` and the debugger's listings decode through it. Everything else is the
   standard library.
-- No cgo, no C, no external toolchain at runtime.
+- No cgo and no C. The standalone encoder paths (`gasm asm --format raw` and `--format
+  elf`) need no Go installation; `gasm verify --ground-truth`, `gasm verify --fuzz`,
+  `gasm audit-instructions` and `gasm asm --format goobj` resolve through the installed
+  Go toolchain.
 - The parser, lexer and formatter are hand-written; the `arch` instruction tables are
   generated only by `_gen/gen.go` (`just gen`) and never edited by hand.
 - Assembly committed to the repository goes through `gasm fmt` and `gasm lint`, so a
@@ -110,8 +117,8 @@ Workflows live in `.gitea/workflows/` and run on the project's own runners:
 
 | Workflow | Trigger | What it does |
 |---|---|---|
-| Test | push or pull request to `development` | build, format check, vet, modernisation, the test suite with the coverage floor |
-| Release | a `v*` tag | the same gates as Test, then the matrix build, the proven version and the release itself; the race detector runs locally in `just gates` before the tag is cut |
+| Test | push or pull request to `development` | build, format check, vet, modernisation, the test suite with the coverage floor, the CLI and debugger tests outside the profile, then the oracle-parity rerun against `go tool asm` |
+| Release | a `v*` tag | the same gates as Test minus the oracle-parity step, then the matrix build, the version smoke test and the release itself; the race detector runs locally in `just gates` before the tag is cut |
 
 The local equivalent is `just gates`, which is the same set plus the race detector. The
 race detector also has its own workflow, dispatched by hand; it never runs on a push or a

README.md

@@ -5,23 +5,25 @@
 > output formats and behaviour can change without warning at any time.
 > A 1.0.0 release is light years away. Nothing in this document is a
 > stability promise. For all of that, this is not a paper project: gasm
-> is already in active use and is tested on real assembly work.
+> is already in active use and is tested on real assembly work. Only
+> amd64 is validated on real hardware; the other three architectures run
+> under emulation ([Validation status](#validation-status)).
 
 **GAsm** is Go's Plan 9 assembler, and Go ships it without tooling:
-there is no formatter, no linter, no static analyser, no standalone
-assembler and no debugger for `.s` files. Developers write assembly
-blind, validate it by benchmark, and debug it by print statement.
-gasm-devkit is the missing toolkit: a single, self-contained binary,
-`gasm`, that serves both purposes.
+there is no formatter, no linter and no debugger for `.s` files, and no
+assembler that works without a Go installation. Developers write
+assembly blind, validate it by benchmark, and debug it by print
+statement. gasm-devkit is the missing toolkit: a single, self-contained
+binary, `gasm`, that serves both purposes.
 
 - **Help develop Plan 9 assembly.** Formatting, linting, disassembly,
   dynamic verification, a source-level debugger and a language server,
   for `.s` files in Go programs.
 - **Use Plan 9 assembly outside the Go toolchain.** `gasm asm` encodes
-  on its own, with no Go installation in the loop, and writes raw
-  images, linkable ELF objects with DWARF5 debug sections, or the Go
+  on its own and writes raw images or linkable ELF objects with DWARF5
+  debug sections, with no Go installation in the loop; the Go
   toolchain's own GOOBJ format, which `go build` consumes in place of
-  the toolchain's output.
+  the toolchain's output, needs the installed toolchain.
 
 ## Why Plan 9 assembly
 
@@ -69,12 +71,14 @@ to give that syntax the tooling it deserves.
   operating recursively on directories the way `go fmt` does.  `-l` lists
   files whose formatting differs and `-d` prints a unified diff.
 - **Linter.**  `gasm lint` runs 18 conservative static checks, among them
-  `undefined-label`, `abi-argsize` (declared frame vs the `// func` signature),
-  `register-clobber` (Go ABI register liveness over the control-flow graph),
-  `stack-imbalance`, `abi0-register-args` and `unencodable-instruction`.
+  `undefined-label`, `abi-argsize` (declared argument area vs the `// func`
+  signature), `register-clobber` (Go ABI register liveness over the
+  control-flow graph), `stack-imbalance`, `abi0-register-args` and
+  `unencodable-instruction`.
 - **Standalone assembler.**  `gasm asm` encodes all four architectures without
-  the Go toolchain and writes raw images, linkable ELF objects (with DWARF5
-  debug sections) or the Go toolchain's own GOOBJ format, which `go build`
+  the Go toolchain and writes raw images or linkable ELF objects (with DWARF5
+  debug sections) with no Go installation needed, or the Go toolchain's own
+  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.
@@ -86,7 +90,8 @@ to give that syntax the tooling it deserves.
   byte-for-byte ground-truth comparison of the machine code.
 - **Debugger.**  `gasm debug` is a source-level ptrace debugger with
   breakpoints (optionally conditional), hardware watchpoints, register and
-  memory inspection, and headless script runs with label-level coverage.
+  memory inspection, and headless script runs that report instruction and
+  label coverage.
 - **Language server.**  `gasm lsp` serves completion, hover, document symbols,
   push and pull diagnostics, semantic-token highlighting, go-to-definition,
   find references, rename, formatting, inlay hints, code actions, signature
@@ -119,10 +124,38 @@ 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 108 of 627 files (17.2 %)
+`gasm audit-instructions --corpus` reports 127 of 627 files (20.3 %)
 assembling for every target architecture today, with the top failure
 reasons per architecture; the number moves with every release.
 
+### Validation status
+
+**Only amd64 is validated on real hardware.** The other three
+architectures are validated under qemu-user emulation, because the
+project owns no arm64, riscv64 or loong64 machine, and emulation is the
+only substitute available for the hardware. The distinction matters and
+is stated rather than implied: everything below is a claim about what has
+actually been executed.
+
+| Layer | amd64 | arm64, riscv64, loong64 |
+|---|---|---|
+| Encoding: byte-for-byte against `go tool asm` | native hardware | native hardware (the toolchain cross-assembles any GOARCH on any host) |
+| Execution: JIT calls, ABI checks, differential fuzzing | native hardware | qemu-user emulation |
+| Debugger: ptrace tracing, breakpoints, watchpoints, coverage | native hardware | emulation cannot run ptrace; the layer compiles and its architecture-neutral units run under `go test ./...`, nothing more |
+
+Consequences, stated plainly. An emulator is a model of a CPU, not the
+CPU: instruction semantics are implemented in software and can differ
+from silicon in ways a test suite does not reveal. A kernel that passes
+under qemu-user is therefore not proven correct on real hardware, and a
+discrepancy found on real hardware is a defect in gasm, reported like any
+other. Encoding parity is the exception: the byte comparison against the
+toolchain runs on the host for every architecture, so no emulator stands
+between the claim and the evidence. The debugger is the weakest case: on
+the three emulated architectures its per-architecture ptrace code has
+been compiled and read, never executed. Its architecture-neutral units
+run under `go test ./...`, which the race workflow and a manual run
+perform; the default `just test` gate does not sweep `./debug/...`.
+
 ## Direction
 
 The plan, in the order it is being worked:
@@ -134,7 +167,8 @@ The plan, in the order it is being worked:
   an extended instruction set the toolchain does not know at all. The
   toolchain-derived tables stay generated and untouched; only the
   extended instructions are hand-maintained, with their own spellings
-  and encoders, verified by execution on real hardware because the
+  and encoders, verified by execution (on real hardware for amd64, under
+  emulation for the rest, per the validation status above) because the
   toolchain offers no ground truth to compare against. The gaps exist
   on every architecture, amd64 included.
 - **Full GOOBJ and ELF compilation.**  The destination is a complete,
@@ -205,7 +239,7 @@ gasm verify --ground-truth k.s          # byte-for-byte vs go tool asm
 gasm verify --fuzz k.s                  # differential fuzz vs the go tool asm build
 gasm debug --func name k.s              # interactive debugger
 gasm debug --func name --script cmds.txt --timeout 30s k.s   # headless run
-gasm debug --func name --cover k.s      # which labels did execution reach?
+gasm debug --func name --cover k.s      # instruction and label coverage
 gasm diff a.s b.s                       # compare machine code byte-for-byte
 gasm diff --map wideCopyAVX2=wideCopyAVX512 avx2.s avx512.s
 gasm profile k.s                        # show basic-block structure
@@ -243,7 +277,8 @@ recipe.
 
 - [docs/CLI.md](docs/CLI.md): full command reference
 - man pages: `just install-man` installs gasm(1) and one page per command
-  into ~/.local/share/man (MANDIR overrides); `just uninstall-man` removes
+  except `version`, which is documented inside gasm(1) instead, into
+  ~/.local/share/man (MANDIR overrides); `just uninstall-man` removes
   them
 - [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md): components and data flow
 - [docs/DEVELOPMENT.md](docs/DEVELOPMENT.md): development setup and recipes

SECURITY.md

@@ -7,7 +7,7 @@ releases do not receive them.
 
 | Version | Supported |
 |---|---|
-| 0.33.0 | yes |
+| 0.34.0 | yes |
 | older releases | no |
 
 ## Reporting a vulnerability
@@ -29,7 +29,8 @@ Include:
 - You are kept informed while the fix is being made, and told when it ships.
 - The fix is released before the details are published, and the timing is agreed with
   you.
-- The reporter is credited in the release notes unless they ask otherwise.
+- The fix ships without naming you: the project keeps no credits list, so the release
+  notes, the changelog and the commits name no reporter.
 
 ## Out of scope
 

arch/arch.go

@@ -55,6 +55,7 @@ const (
 	Mask                    // AVX-512 mask register (K)
 	Float                   // arm64 floating-point register (F)
 	VecARM                  // arm64 SIMD/vector register (V)
+	VecSIMD                 // architecture-neutral SIMD/vector register (LoongArch LSX/LASX)
 	Special                 // architecture-special register
 )
 
@@ -73,6 +74,8 @@ func (c RegClass) String() string {
 		return "float"
 	case VecARM:
 		return "vector (arm64)"
+	case VecSIMD:
+		return "vector"
 	case Special:
 		return "special"
 	default:

arch/arm64.go

@@ -145,7 +145,7 @@ func arm64Curated() []Instr {
 	for _, op := range []string{
 		"LDAXR", "LDAXRB", "LDAXRH", "LDAXRW", "STXR", "STXRB", "STXRH", "STXRW",
 		"LDAR", "LDARB", "LDARH", "LDARW", "STLR", "STLRB", "STLRH", "STLRW",
-		"LDADD", "LDCLR", "LDEOR", "LDSET", "SWP", "CAS", "CASAL", "CASL", "CASAL",
+		"LDADD", "LDCLR", "LDEOR", "LDSET", "SWP", "CAS", "CASAL", "CASL",
 	} {
 		t = append(t, i(op, "Atomic memory operation"))
 	}

arch/loong64.go

@@ -31,10 +31,10 @@ func loong64Registers() []Register {
 		add(fmt.Sprintf("F%d", i), Float, "floating-point register")
 	}
 	for i := 0; i <= 31; i++ {
-		add(fmt.Sprintf("V%d", i), VecARM, "LSX 128-bit vector register")
+		add(fmt.Sprintf("V%d", i), VecSIMD, "LSX 128-bit vector register")
 	}
 	for i := 0; i <= 31; i++ {
-		add(fmt.Sprintf("X%d", i), VecARM, "LASX 256-bit vector register")
+		add(fmt.Sprintf("X%d", i), VecSIMD, "LASX 256-bit vector register")
 	}
 	return regs
 }

asm/aarch64_goobj_test.go

@@ -4,6 +4,7 @@
 package asm
 
 import (
+	"encoding/binary"
 	"os"
 	"os/exec"
 	"path/filepath"
@@ -61,6 +62,62 @@ TEXT ·add(SB), NOSPLIT, $0-24
 	}
 }
 
+// TestGOObjectAARCH64PairReloc pins the ADRP-pair relocation shape against
+// the toolchain's own object for the same source: exactly one R_ADDRARM64
+// of Siz 8 at the ADRP word (cmd/internal/obj/arm64/asm7.go adds a single
+// Siz-8 relocation per pair and the linker patches both instructions from
+// it).  gasm's assembler records the ADRP+ADD form as two word relocs; the
+// emitter must coalesce them, not emit two Siz-4 records.
+func TestGOObjectAARCH64PairReloc(t *testing.T) {
+	f, errs := parser.Parse("gv_arm64.s", `
+#include "textflag.h"
+
+TEXT ·getv(SB), NOSPLIT, $0-8
+	MOVD $v<>(SB), R4
+	MOVD R4, ret+0(FP)
+	RET
+
+GLOBL v<>(SB), RODATA, $8
+DATA v<>+0(SB)/8, $7
+`)
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFileARM64(f)
+	if err != nil {
+		t.Fatalf("AssembleFileARM64: %v", err)
+	}
+	obj, err := img.GOObjectAARCH64("main", "gv_arm64.s")
+	if err != nil {
+		t.Fatalf("GOObjectAARCH64: %v", err)
+	}
+	v := openGoobj(t, obj)
+	relocs := v.blk(blkReloc)
+	le := binary.LittleEndian
+	// Two DWARF relocs on the lines/DIE symbols, then the code's one pair
+	// relocation.
+	if len(relocs) != 3*23 {
+		t.Fatalf("relocs = %d bytes, want three entries", len(relocs))
+	}
+	cr := relocs[2*23:]
+	if off := int32(le.Uint32(cr[0:])); off != 0 {
+		t.Errorf("pair reloc off = %d, want 0 (the ADRP word)", off)
+	}
+	if siz := cr[4]; siz != 8 {
+		t.Errorf("pair reloc siz = %d, want 8", siz)
+	}
+	if typ := le.Uint16(cr[5:]); typ != relocArm64Addr {
+		t.Errorf("pair reloc type = %d, want %d (R_ADDRARM64)", typ, relocArm64Addr)
+	}
+	if pkg := le.Uint32(cr[15:]); pkg != pkgIdxSelf {
+		t.Errorf("pair reloc PkgIdx = %#x, want pkgIdxSelf", pkg)
+	}
+	// The GLOBL is the first package definition.
+	if sym := le.Uint32(cr[19:]); sym != 0 {
+		t.Errorf("pair reloc SymIdx = %d, want 0 (the GLOBL definition)", sym)
+	}
+}
+
 // TestGOObjectAARCH64Link does an end-to-end link test: it cross-compiles a
 // Go program for arm64, substitutes the gasm-produced object into the package
 // archive, re-links with cmd/link, and verifies the symbol appears in the
@@ -79,6 +136,14 @@ TEXT ·add(SB), NOSPLIT, $0-24
 	ADD R5, R4, R4
 	MOVD R4, ret+16(FP)
 	RET
+
+TEXT ·getv(SB), NOSPLIT, $0-8
+	MOVD $v<>(SB), R4
+	MOVD R4, ret+0(FP)
+	RET
+
+GLOBL v<>(SB), RODATA, $8
+DATA v<>+0(SB)/8, $7
 `
 	if err := os.WriteFile(filepath.Join(dir, "main_arm64.s"), []byte(asmSrc), 0o644); err != nil {
 		t.Fatal(err)
@@ -86,11 +151,15 @@ TEXT ·add(SB), NOSPLIT, $0-24
 	mainSrc := `package main
 
 func add(a, b int64) int64
+func getv() *int64
 
 func main() {
 	if add(20, 22) != 42 {
 		panic("bad add")
 	}
+	if getv() == nil {
+		panic("bad getv")
+	}
 }
 `
 	if err := os.WriteFile(filepath.Join(dir, "main.go"), []byte(mainSrc), 0o644); err != nil {

asm/arm64_assemble.go

@@ -189,7 +189,7 @@ func arm64InstrSize(instr *ast.Instr, fi arm64FrameInfo) int {
 		return arm64MovSize(mnem, ops, fi)
 	case "ADD", "ADDW", "SUB", "SUBW", "AND", "ANDW", "ORR", "ORRW", "EOR", "EORW":
 		if len(ops) >= 2 && isImmOperand(ops[0]) {
-			v := immFromOperand(ops[0])
+			v := arm64Imm64(ops[0])
 			// Small immediate (0..4095 or -2048..-1) fits in one instruction.
 			if v >= 0 && v <= 0xFFF {
 				return 4
@@ -221,7 +221,11 @@ func encodeARM64Instr(instr *ast.Instr, pc int, offsets map[string]int, fi arm64
 		if len(ops) != 1 {
 			return nil, fmt.Errorf("WORD expects 1 operand, got %d", len(ops))
 		}
-		return a64wordLE(uint32(immFromOperand(ops[0]))), nil
+		w := arm64Imm64(ops[0])
+		if w < 0 || w > 0xFFFFFFFF {
+			return nil, fmt.Errorf("WORD: immediate %d does not fit a 32-bit word", w)
+		}
+		return a64wordLE(uint32(w)), nil
 	case "B", "JMP":
 		return encodeARM64Branch(mnem, ops, pc, offsets, false, relocs, resolve)
 	case "BL", "CALL":
@@ -249,14 +253,19 @@ func encodeARM64Instr(instr *ast.Instr, pc int, offsets map[string]int, fi arm64
 		}
 	}
 
+	// Shifts: immediate forms alias SBFM/UBFM/EXTR, register forms are the
+	// two-source LSLV/LSRV/ASRV/RORV.
+	if enc, ok := a64InstrTable[mnem]; ok && enc.format == a64FShift {
+		return encodeARM64Shift(mnem, enc.op, ops)
+	}
+
+	// Multiply-accumulate: MADD/MSUB Rm, Ra, Rn, Rd.
+	if enc, ok := a64InstrTable[mnem]; ok && enc.format == a64FDPR4 {
+		return encodeARM64MAddSub(mnem, enc.op, ops)
+	}
+
 	// Register-register data processing.
-	// ASR/LSL/LSR/ROR with immediate operands use bitfield encoding (SBFM/UBFM).
 	if enc, ok := a64InstrTable[mnem]; ok && enc.format == a64FDPSR {
-		isShift := mnem == "ASR" || mnem == "ASRW" || mnem == "LSL" || mnem == "LSLW" ||
-			mnem == "LSR" || mnem == "LSRW" || mnem == "ROR" || mnem == "RORW"
-		if isShift && len(ops) >= 2 && isImmOperand(ops[0]) {
-			return encodeARM64Bitfield(mnem, enc.op, ops)
-		}
 		return encodeARM64DPSR(mnem, enc.op, ops)
 	}
 
@@ -305,7 +314,8 @@ func encodeARM64Instr(instr *ast.Instr, pc int, offsets map[string]int, fi arm64
 		return encodeARM64CRC32(mnem, enc.op, ops)
 	}
 
-	// Exclusive load/store (LDXR, STXR, LDAXR, STLXR).
+	// Exclusive load/store (LDXR, STXR, LDAXR, STLXR and the register-pair
+	// forms LDXP, STXP).
 	if enc, ok := a64InstrTable[mnem]; ok && enc.format == a64FExcl {
 		return encodeARM64Excl(mnem, enc.op, ops)
 	}
@@ -478,6 +488,88 @@ func encodeARM64DPSR(mnem string, baseOp uint32, ops []*ast.Operand) ([]byte, er
 	return nil, fmt.Errorf("%s expects 2 or 3 operands, got %d", mnem, len(ops))
 }
 
+// encodeARM64Shift encodes LSL/LSR/ASR/ROR in both widths.  The operand order
+// is source first, destination last: OP $sh|Rm, Rn, Rd or OP $sh|Rm, Rd.
+// With an immediate the shift is the SBFM/UBFM (ROR: EXTR) alias, with a
+// register it is the data-processing (2 source) LSLV/LSRV/ASRV/RORV; the
+// two-source opcode rides the same 0xd6<<21 field as SDIV/UDIV, with
+// LSLV=0b001000, LSRV=0b001001, ASRV=0b001010, RORV=0b001011 at bits 15:10.
+func encodeARM64Shift(mnem string, baseOp uint32, ops []*ast.Operand) ([]byte, error) {
+	if len(ops) != 2 && len(ops) != 3 {
+		return nil, fmt.Errorf("%s expects 2 or 3 operands, got %d", mnem, len(ops))
+	}
+	rn := arm64RegNum(operandRegName(ops[1]))
+	rd := arm64RegNum(operandRegName(ops[len(ops)-1]))
+	if rn < 0 || rd < 0 {
+		return nil, fmt.Errorf("invalid register operand in %s", mnem)
+	}
+
+	if isImmOperand(ops[0]) {
+		width := uint32(64)
+		if strings.HasSuffix(mnem, "W") {
+			width = 32
+		}
+		sh := arm64Imm64(ops[0])
+		if sh < 0 || uint32(sh) >= width {
+			return nil, fmt.Errorf("%s: shift amount %d out of range for %d-bit form", mnem, sh, width)
+		}
+		switch mnem {
+		case "LSL", "LSLW":
+			// UBFM Rd, Rn, #(-sh) mod W, #(W-1)-sh
+			immr := (width - uint32(sh)) % width
+			return a64wordLE(baseOp | immr<<16 | (width-1-uint32(sh))<<10 | uint32(rn)<<5 | uint32(rd)), nil
+		case "LSR", "LSRW":
+			// UBFM Rd, Rn, #sh, #(W-1)
+			return a64wordLE(baseOp | uint32(sh)<<16 | (width-1)<<10 | uint32(rn)<<5 | uint32(rd)), nil
+		case "ASR", "ASRW":
+			// SBFM Rd, Rn, #sh, #(W-1)
+			return a64wordLE(baseOp | uint32(sh)<<16 | (width-1)<<10 | uint32(rn)<<5 | uint32(rd)), nil
+		default:
+			// ROR, RORW: EXTR Rd, Rn, Rn, #sh (Rm = Rn, imms = sh).
+			return a64wordLE(baseOp | uint32(rn)<<16 | uint32(sh)<<10 | uint32(rn)<<5 | uint32(rd)), nil
+		}
+	}
+
+	rm := arm64RegNum(operandRegName(ops[0]))
+	if rm < 0 {
+		return nil, fmt.Errorf("invalid register operand in %s", mnem)
+	}
+	op2 := uint32(8) // LSLV
+	switch mnem {
+	case "LSR", "LSRW":
+		op2 = 9 // LSRV
+	case "ASR", "ASRW":
+		op2 = 10 // ASRV
+	case "ROR", "RORW":
+		op2 = 11 // RORV
+	}
+	sf := uint32(1)
+	if strings.HasSuffix(mnem, "W") {
+		sf = 0
+	}
+	return a64wordLE(sf<<31 | 0xd6<<21 | op2<<10 | uint32(rm)<<16 | uint32(rn)<<5 | uint32(rd)), nil
+}
+
+// encodeARM64MAddSub encodes MADD/MSUB/MADDW/MSUBW.  The toolchain's operand
+// order is Rm, Ra, Rn, Rd (its optab case 15 comment says exactly that), so
+// the accumulate register is the SECOND operand: base | Rm<<16 | Ra<<10 |
+// Rn<<5 | Rd.  The optab has no shorter row for these mnemonics, so all four
+// operands are mandatory; MUL's two-operand spelling (Ra = ZR) belongs to the
+// MUL mnemonic, not to these.
+func encodeARM64MAddSub(mnem string, baseOp uint32, ops []*ast.Operand) ([]byte, error) {
+	if len(ops) != 4 {
+		return nil, fmt.Errorf("%s expects 4 operands (Rm, Ra, Rn, Rd), got %d", mnem, len(ops))
+	}
+	rm := arm64RegNum(operandRegName(ops[0]))
+	ra := arm64RegNum(operandRegName(ops[1]))
+	rn := arm64RegNum(operandRegName(ops[2]))
+	rd := arm64RegNum(operandRegName(ops[3]))
+	if rm < 0 || rn < 0 || ra < 0 || rd < 0 {
+		return nil, fmt.Errorf("invalid register operand in %s", mnem)
+	}
+	return a64wordLE(baseOp | uint32(rm)<<16 | uint32(ra)<<10 | uint32(rn)<<5 | uint32(rd)), nil
+}
+
 // ---- ADD/SUB immediate ----
 
 // encodeARM64AddSubImm encodes an ADD/SUB immediate instruction.
@@ -485,7 +577,7 @@ func encodeARM64AddSubImm(mnem string, ops []*ast.Operand) ([]byte, error) {
 	if len(ops) != 2 && len(ops) != 3 {
 		return nil, fmt.Errorf("%s expects 2 or 3 operands, got %d", mnem, len(ops))
 	}
-	v := immFromOperand(ops[0])
+	v := arm64Imm64(ops[0])
 	rd := arm64RegNum(operandRegName(ops[len(ops)-1]))
 	rn := rd
 	if len(ops) == 3 {
@@ -529,6 +621,8 @@ func encodeARM64AddSubImm(mnem string, ops []*ast.Operand) ([]byte, error) {
 	if v >= 0 && v <= 0xFFF000 && v&0xFFF == 0 {
 		return a64wordLE(a64AddSub(sf, op, S, 1, uint32(v>>12), uint32(rn), uint32(rd))), nil
 	}
+	// The imm12 field cannot carry the value; rejecting (rather than
+	// truncating) matches the toolchain, which reports the same shape.
 	return nil, fmt.Errorf("%s: immediate %d out of range for single instruction", mnem, v)
 }
 
@@ -615,14 +709,15 @@ func arm64MovSize(mnem string, ops []*ast.Operand, fi arm64FrameInfo) int {
 		if src.Imm.Sym != nil && src.Imm.Sym.Pseudo == "SB" {
 			return 8 // ADRP + ADD
 		}
-		v := arm64Imm64(src)
-		if v == 0 {
+		// Size the immediate exactly as the encoder will emit it: multi-chunk
+		// values expand to up to four words and the W forms truncate first.
+		// Anything else would desynchronise the label offsets of pass 1 from
+		// the bytes pass 2 lays down, corrupting every later branch.
+		b, err := encodeARM64LoadImm(31, arm64Imm64(src), mnem)
+		if err != nil {
 			return 4
 		}
-		if arm64Movcon(v) >= 0 || arm64Movcon(^v) >= 0 {
-			return 4
-		}
-		return 8 // MOVZ + MOVK
+		return len(b)
 	case src.Addr.Sym != nil && src.Addr.Sym.Pseudo == "SB":
 		return 8 // ADRP + LDR
 	case dst.Addr.Sym != nil && dst.Addr.Sym.Pseudo == "SB":
@@ -638,7 +733,7 @@ func arm64MovSize(mnem string, ops []*ast.Operand, fi arm64FrameInfo) int {
 		if !ok {
 			lt = a64LoadTable["MOVD"] // the MOV pseudo is a 64-bit access
 		}
-		scale := int32(1) << uint(lt.size)
+		scale := int64(1) << uint(lt.size)
 		if off >= 0 && off%scale == 0 && off/scale < 4096 {
 			return 4
 		}
@@ -655,51 +750,60 @@ func arm64MovSize(mnem string, ops []*ast.Operand, fi arm64FrameInfo) int {
 }
 
 // encodeARM64LoadImm loads an immediate into a register, matching the
-// toolchain's MOVZ/MOVN/MOVK sequence.
+// toolchain's MOVZ/MOVN/MOVK sequence.  W forms truncate to 32 bits first and
+// every classification (movcon, complement, chunk count) runs on the truncated
+// value, so a 32-bit immediate never reaches the 64-bit halves: MOVW $-1
+// truncates to 0xFFFFFFFF, whose complement is a single zero chunk, and encodes
+// as MOVN W, #0.
 func encodeARM64LoadImm(rd int, v int64, mnem string) ([]byte, error) {
 	d := v
-	// For 32-bit MOVW, zero-extend.
+	sf := uint32(1) // 64-bit
 	if mnem == "MOVW" || mnem == "MOVWU" {
 		d = int64(uint32(v))
+		sf = 0
 	}
 
 	if d == 0 {
 		// ORR Rd, ZR, ZR (MOV $0, Rd)
 		op := uint32(1<<31 | 1<<29 | 0x0a<<24) // ORR 64-bit
-		if mnem == "MOVW" || mnem == "MOVWU" {
+		if sf == 0 {
 			op = 0<<31 | 1<<29 | 0x0a<<24 // ORR 32-bit
 		}
 		return a64wordLE(op | 31<<16 | 31<<5 | uint32(rd)), nil
 	}
 
-	sf := uint32(1) // 64-bit
-	if mnem == "MOVW" || mnem == "MOVWU" {
-		sf = 0
-	}
-
-	// The Go toolchain classifies immediates:
-	// - C_ABCON0 (0 < v ≤ 4095): bitmask first for positive values
-	// - Negative values: MOVN first, then bitmask
-	// - C_MOVCON (movcon-eligible, outside ABCON range): MOVZ/MOVN first
-	tryBitmaskFirst := d > 0 && d <= 0xFFF
+	// The Go toolchain classifies immediates (asm7.go conclass):
+	// - inside the imm12/shifted-imm12 "addcon" band (C_ABCON0/C_ABCON,
+	//   0 < v ≤ 4095 or a 4096 multiple up to 0xFFF000): bitmask first, so
+	//   `MOVD $4096, R27` is ORR $4096, not MOVZ $(1<<12)
+	// - outside that band: MOVZ/MOVN first (C_MOVCON before C_BITCON), and
+	//   negative values reach MOVN before the bitmask test
+	tryBitmaskFirst := d > 0 && (d <= 0xFFF || (d&0xFFF == 0 && d <= 0xFFF000))
 
 	if tryBitmaskFirst {
-		// Small immediate: try bitmask first (Go uses ORR for values like $1, $256).
+		// Addcon-band immediate: try bitmask first (Go uses ORR for values
+		// like $1, $256 and $65536).
 		N, immr, imms, ok := arm64Bitmask(uint64(d), int(sf))
 		if ok {
 			return a64wordLE(sf<<31 | 1<<29 | 0x24<<23 | N<<22 | immr<<16 | imms<<10 | 31<<5 | uint32(rd)), nil
 		}
 	}
 
-	// Try MOVZ (single non-zero 16-bit chunk).
+	// Try MOVZ (single non-zero 16-bit chunk) and MOVN (single non-0xFFFF
+	// chunk of the complement).  The W forms must look inside the 32-bit
+	// window only, so the complement is masked to the operand width; d is
+	// already truncated and needs no mask.
+	width := uint64(0xFFFFFFFF)
+	if sf == 1 {
+		width = 0xFFFFFFFFFFFFFFFF
+	}
 	s := arm64Movcon(d)
 	if s >= 0 {
 		return a64wordLE(a64MoveWide(sf, 2, uint32(s>>4), uint32((d>>uint(s))&0xFFFF), uint32(rd))), nil
 	}
-	// Try MOVN (single non-0xFFFF 16-bit chunk of ^d).
-	sn := arm64Movcon(^d)
+	sn := arm64Movcon(^d & int64(width))
 	if sn >= 0 {
-		return a64wordLE(a64MoveWide(sf, 0, uint32(sn>>4), uint32((^d>>uint(sn))&0xFFFF), uint32(rd))), nil
+		return a64wordLE(a64MoveWide(sf, 0, uint32(sn>>4), uint32(((^d)>>uint(sn))&0xFFFF), uint32(rd))), nil
 	}
 
 	// For values outside the bitmask-first range that are not movcon: try bitmask.
@@ -710,7 +814,7 @@ func encodeARM64LoadImm(rd int, v int64, mnem string) ([]byte, error) {
 		}
 	}
 
-	// Multi-instruction: MOVZ + MOVK for each non-zero16-bit chunk.
+	// Multi-instruction: MOVZ + MOVK for each non-zero 16-bit chunk.
 	var ws []uint32
 	first := true
 	for i := range 4 {
@@ -805,7 +909,7 @@ func arm64Bitmask(v uint64, sf int) (N, immr, imms uint32, ok bool) {
 // Integer → integer: ORR Rd, ZR, Rs.
 // FP → FP: FMOV Fd, Fn (FP data processing).
 // FP ↔ GP: FMOV general (FPCVTI encoding).
-// Go Plan 9 syntax: MOV dst, src (first operand = destination).
+// Go Plan 9 syntax is source first, destination last: MOV src, dst.
 func encodeARM64RegMove(mnem string, src, dst *ast.Operand) ([]byte, error) {
 	rs := arm64RegNum(operandRegName(src))
 	rd := arm64RegNum(operandRegName(dst))
@@ -826,8 +930,7 @@ func encodeARM64RegMove(mnem string, src, dst *ast.Operand) ([]byte, error) {
 	}
 
 	// GP ↔ FP: FMOV general (FPCVTI encoding).
-	// Go syntax: FMOV FPdst, GPsrc or FMOV GPdst, FPsrc.
-	// First operand = destination, second = source.
+	// Go syntax: FMOV GPsrc, FPdst or FMOV FPsrc, GPdst, source first.
 	if sc == arm64ClsFP && dc == arm64ClsGR {
 		// FP → GP: FMOV Wd/Xd, Sn/Dn. opcode bits[20:16]=6.
 		sf, typ := uint32(0), uint32(0)
@@ -867,7 +970,7 @@ func encodeARM64MemOp(mnem string, mem *ast.Operand, reg int, load bool, fi arm6
 		lt = a64LoadTable["MOVD"]
 	}
 
-	scale := int32(1) << uint(lt.size)
+	scale := int64(1) << uint(lt.size)
 	storeOpc := a64StoreOpc(lt)
 	var opc int
 	if load {
@@ -880,30 +983,31 @@ func encodeARM64MemOp(mnem string, mem *ast.Operand, reg int, load bool, fi arm6
 		return a64wordLE(a64LSU(uint32(lt.size), uint32(lt.V), uint32(opc), uint32(off/scale), uint32(rn), uint32(reg))), nil
 	}
 	if off >= -256 && off <= 255 {
-		return a64wordLE(a64LSUnscaled(lt.size, lt.V, opc, off, rn, reg)), nil
+		return a64wordLE(a64LSUnscaled(lt.size, lt.V, opc, int32(off), rn, reg)), nil
 	}
 	// Large offset: materialise the base in REGTMP (R27) the way the
-	// toolchain does and access what remains.
+	// toolchain does and access what remains.  The ADD offsets from the
+	// operand's own base register, [SP] and [Rn] alike.
 	addImm, addShift, access, ok := arm64SplitOffset(off, scale)
 	if !ok {
 		return nil, fmt.Errorf("%s: offset %d out of range (literal pool not supported)", mnem, off)
 	}
 	return a64WordsLE(
-		a64AddSub(1, 0, 0, addShift, uint32(addImm), 31, 27), // ADD $addImm<<shift, SP, R27
+		a64AddSub(1, 0, 0, addShift, addImm, uint32(rn), 27), // ADD $addImm<<shift, Rn, R27
 		a64LSU(uint32(lt.size), uint32(lt.V), uint32(opc), uint32(access/scale), 27, uint32(reg)),
 	), nil
 }
 
-// arm64SplitOffset decomposes an out-of-range frame offset for a REGTMP
-// base: an ADD (plain, or shifted left by 12) brings SP near the target and
-// the access covers what remains.  ok is false when no decomposition exists
-// (offsets at or beyond 16 MiB, where the toolchain falls back to a literal
-// pool).
-func arm64SplitOffset(off int32, scale int32) (addImm, addShift uint32, access int32, ok bool) {
+// arm64SplitOffset decomposes an out-of-range offset for a REGTMP base: an
+// ADD (plain, or shifted left by 12) brings the base near the target and the
+// access covers what remains.  ok is false when no decomposition exists
+// (negative offsets, or beyond 16 MiB, where the toolchain falls back to a
+// literal pool).
+func arm64SplitOffset(off int64, scale int64) (addImm, addShift uint32, access int64, ok bool) {
 	if off < 0 {
 		return 0, 0, 0, false
 	}
-	// Plain ADD: bring SP to within the largest scaled access.
+	// Plain ADD: bring the base to within the largest scaled access.
 	l := min(off, 4095*scale)
 	l -= l % scale
 	if a := off - l; a <= 4095 {
@@ -987,12 +1091,15 @@ func arm64Imm64(op *ast.Operand) int64 {
 }
 
 // arm64MemWithFrame resolves a memory operand, translating FP/SP pseudo-
-// registers via the frame mapping.
-func arm64MemWithFrame(op *ast.Operand, fi arm64FrameInfo) (rn int, off int32) {
+// registers via the frame mapping.  The offset stays 64-bit: the AST carries
+// int64 displacements and truncating here would wrap offsets beyond 2^31
+// silently.
+func arm64MemWithFrame(op *ast.Operand, fi arm64FrameInfo) (rn int, off int64) {
 	if op.Addr.Sym != nil && op.Addr.Sym.Pseudo != "" {
-		return arm64ResolvePseudo(op.Addr.Sym, fi)
+		base, pseudo := arm64ResolvePseudo(op.Addr.Sym, fi)
+		return base, int64(pseudo)
 	}
-	return arm64RegNum(op.Addr.Base), int32(op.Addr.Offset)
+	return arm64RegNum(op.Addr.Base), op.Addr.Offset
 }
 
 // arm64Label returns the label name of an operand.
@@ -1068,7 +1175,7 @@ func encodeARM64FPCmp(mnem string, baseOp uint32, ops []*ast.Operand) ([]byte, e
 		return nil, fmt.Errorf("%s expects 2 operands, got %d", mnem, len(ops))
 	}
 	// Check if first operand is #0 (compare with zero): FCMP $0.0, Fn.
-	if isImmOperand(ops[0]) && immFromOperand(ops[0]) == 0 {
+	if isImmOperand(ops[0]) && arm64Imm64(ops[0]) == 0 {
 		rn := arm64RegNum(operandRegName(ops[1]))
 		if rn < 0 {
 			return nil, fmt.Errorf("invalid register operand in %s", mnem)
@@ -1105,8 +1212,11 @@ func encodeARM64FPCCmp(mnem string, baseOp uint32, ops []*ast.Operand) ([]byte,
 	if rm < 0 || rn < 0 {
 		return nil, fmt.Errorf("invalid register operand in %s", mnem)
 	}
-	nzcv := uint32(immFromOperand(ops[3]))
-	return a64wordLE(baseOp | uint32(rm)<<16 | cond<<12 | uint32(rn)<<5 | nzcv&0xF), nil
+	nzcv := arm64Imm64(ops[3])
+	if nzcv < 0 || nzcv > 0xF {
+		return nil, fmt.Errorf("%s: nzcv %d out of range (0..15)", mnem, nzcv)
+	}
+	return a64wordLE(baseOp | uint32(rm)<<16 | cond<<12 | uint32(rn)<<5 | uint32(nzcv)&0xF), nil
 }
 
 // encodeARM64FPSel encodes a FP conditional select.
@@ -1233,32 +1343,94 @@ func encodeARM64CRC32(mnem string, baseOp uint32, ops []*ast.Operand) ([]byte, e
 
 // ---- Atomics encoding ----
 
-// encodeARM64Excl encodes an exclusive load/store instruction.
-// LDXR (Rn), Rt → LDXR Rt, [Rn] (2 operands: mem, reg or reg, mem)
-// STXR Rs, (Rn), Rt → STXR Rs, Rt, [Rn] (3 operands: Rs, mem, Rt-status)
+// arm64ExclMem resolves the memory operand of an exclusive or atomic
+// instruction.  These encodings have no immediate field: the toolchain
+// rejects `LDXR 8(R1), R2` as an illegal combination, so a non-zero offset is
+// reported rather than silently dropped (which would read the wrong address).
+func arm64ExclMem(mnem string, op *ast.Operand) (int, error) {
+	rn, off := arm64MemWithFrame(op, arm64FrameInfo{})
+	if rn < 0 {
+		return 0, fmt.Errorf("invalid memory operand in %s", mnem)
+	}
+	if off != 0 {
+		return 0, fmt.Errorf("%s: offset %d not supported, exclusive and atomic accesses take a plain (Rn) operand", mnem, off)
+	}
+	return rn, nil
+}
+
+// arm64PairOf parses a register-pair operand `(R1, R2)`, reporting false
+// when the operand is not a pair.  The toolchain takes the second register of
+// the pair from the operand's Offset (its C_PAIR class,
+// cmd/internal/obj/arm64/asm7.go cases 58/59).
+func arm64PairOf(op *ast.Operand) (int, int, bool) {
+	raw := strings.TrimSpace(op.Raw)
+	if !strings.HasPrefix(raw, "(") || !strings.HasSuffix(raw, ")") {
+		return -1, -1, false
+	}
+	parts := strings.Split(raw[1:len(raw)-1], ",")
+	if len(parts) != 2 {
+		return -1, -1, false
+	}
+	r1 := arm64RegNum(strings.TrimSpace(parts[0]))
+	r2 := arm64RegNum(strings.TrimSpace(parts[1]))
+	if r1 < 0 || r2 < 0 {
+		return -1, -1, false
+	}
+	return r1, r2, true
+}
+
+// encodeARM64Excl encodes the exclusive load/store family with the operand
+// order the toolchain parses (cmd/internal/obj/arm64/asm7.go cases 58 and 59,
+// and its own spellings in arm64enc.s):
+//
+//	STXR  Rt, (Rn), Rs            store, single register
+//	STXP  (Rt1, Rt2), (Rn), Rs    store, register pair
+//	LDXR  (Rn), Rt                load, single register
+//	LDXP  (Rn), (Rt1, Rt2)        load, register pair
+//
+// Decoded toolchain evidence: `STXR R1, (R2), R3` assembles to 0xc8037c41,
+// whose fields are Rs=3, Rn=2, Rt=1: the FIRST register operand is the data
+// register and the LAST the status register.
 func encodeARM64Excl(mnem string, baseOp uint32, ops []*ast.Operand) ([]byte, error) {
-	// LDXR/STXR have different operand forms.
 	isLoad := strings.HasPrefix(mnem, "LD")
 	if isLoad {
-		// LDXR (Rn), Rt → 2 operands: mem, reg
+		// LDXR (Rn), Rt / LDXP (Rn), (Rt1, Rt2): 2 operands.
 		if len(ops) != 2 {
 			return nil, fmt.Errorf("%s expects 2 operands, got %d", mnem, len(ops))
 		}
-		rn, _ := arm64MemWithFrame(ops[0], arm64FrameInfo{})
+		rn, err := arm64ExclMem(mnem, ops[0])
+		if err != nil {
+			return nil, err
+		}
+		if rt1, rt2, ok := arm64PairOf(ops[1]); ok {
+			// The single-register opcodes pre-set the unused Rs (bits 20:16)
+			// and Rt2 (bits 14:10) fields to 31; the pair forms carry a real
+			// Rt2 and keep Rs at 31.
+			return a64wordLE(baseOp | 0x1F<<16 | uint32(rt2)<<10 | uint32(rn)<<5 | uint32(rt1)), nil
+		}
 		rt := arm64RegNum(operandRegName(ops[1]))
-		if rn < 0 || rt < 0 {
+		if rt < 0 {
 			return nil, fmt.Errorf("invalid operand in %s", mnem)
 		}
 		return a64wordLE(baseOp | uint32(rn)<<5 | uint32(rt)), nil
 	}
-	// STXR Rs, (Rn), Rt → 3 operands: Rs, mem, Rt
+	// STXR Rt, (Rn), Rs / STXP (Rt1, Rt2), (Rn), Rs: 3 operands.
 	if len(ops) != 3 {
 		return nil, fmt.Errorf("%s expects 3 operands, got %d", mnem, len(ops))
 	}
-	rs := arm64RegNum(operandRegName(ops[0]))
-	rn, _ := arm64MemWithFrame(ops[1], arm64FrameInfo{})
-	rt := arm64RegNum(operandRegName(ops[2]))
-	if rs < 0 || rn < 0 || rt < 0 {
+	rn, err := arm64ExclMem(mnem, ops[1])
+	if err != nil {
+		return nil, err
+	}
+	rs := arm64RegNum(operandRegName(ops[2]))
+	if rs < 0 {
+		return nil, fmt.Errorf("invalid operand in %s", mnem)
+	}
+	if rt1, rt2, ok := arm64PairOf(ops[0]); ok {
+		return a64wordLE(baseOp | uint32(rs)<<16 | uint32(rt2)<<10 | uint32(rn)<<5 | uint32(rt1)), nil
+	}
+	rt := arm64RegNum(operandRegName(ops[0]))
+	if rt < 0 {
 		return nil, fmt.Errorf("invalid operand in %s", mnem)
 	}
 	return a64wordLE(baseOp | uint32(rs)<<16 | uint32(rn)<<5 | uint32(rt)), nil
@@ -1272,9 +1444,15 @@ func encodeARM64LSEAtom(mnem string, baseOp uint32, ops []*ast.Operand) ([]byte,
 		return nil, fmt.Errorf("%s expects 3 operands, got %d", mnem, len(ops))
 	}
 	rs := arm64RegNum(operandRegName(ops[0]))
-	rn, _ := arm64MemWithFrame(ops[1], arm64FrameInfo{})
+	if rs < 0 {
+		return nil, fmt.Errorf("invalid operand in %s", mnem)
+	}
+	rn, err := arm64ExclMem(mnem, ops[1])
+	if err != nil {
+		return nil, err
+	}
 	rt := arm64RegNum(operandRegName(ops[2]))
-	if rs < 0 || rn < 0 || rt < 0 {
+	if rt < 0 {
 		return nil, fmt.Errorf("invalid operand in %s", mnem)
 	}
 	return a64wordLE(baseOp | uint32(rs)<<16 | uint32(rn)<<5 | uint32(rt)), nil
@@ -1283,43 +1461,25 @@ func encodeARM64LSEAtom(mnem string, baseOp uint32, ops []*ast.Operand) ([]byte,
 // ---- Bitfield/EXTR encoding ----
 
 // encodeARM64Bitfield encodes a bitfield instruction.
-// ASR/LSL/LSR/ROR $shamt, Rn, Rd → 3 operands: $imm, Rn, Rd
 // BFI/BFXIL/SBFM/UBFM $immr, Rn, $imms, Rd → 4 operands
 func encodeARM64Bitfield(mnem string, baseOp uint32, ops []*ast.Operand) ([]byte, error) {
-	isShift := mnem == "ASR" || mnem == "ASRW" || mnem == "LSL" || mnem == "LSLW" ||
-		mnem == "LSR" || mnem == "LSRW" || mnem == "ROR" || mnem == "RORW"
-
-	if isShift {
-		// ASR $shamt, Rn, Rd → SBFM with immr=shamt, imms=31/63
-		if len(ops) != 3 {
-			return nil, fmt.Errorf("%s expects 3 operands, got %d", mnem, len(ops))
-		}
-		shamt := int(immFromOperand(ops[0]))
-		rn := arm64RegNum(operandRegName(ops[1]))
-		rd := arm64RegNum(operandRegName(ops[2]))
-		if rn < 0 || rd < 0 {
-			return nil, fmt.Errorf("invalid register operand in %s", mnem)
-		}
-		// ASR: SBFM with immr=shamt, imms=31(32-bit) or 63(64-bit)
-		is64 := mnem == "ASR"
-		imms := 31
-		if is64 {
-			imms = 63
-		}
-		return a64wordLE(baseOp | uint32(shamt)<<16 | uint32(imms)<<10 | uint32(rn)<<5 | uint32(rd)), nil
-	}
-
 	// BFI/BFXIL/SBFM/UBFM: 4 operands ($immr, Rn, $imms, Rd)
 	if len(ops) != 4 {
 		return nil, fmt.Errorf("%s expects 4 operands, got %d", mnem, len(ops))
 	}
-	immr := int(immFromOperand(ops[0]))
+	immr := arm64Imm64(ops[0])
 	rn := arm64RegNum(operandRegName(ops[1]))
-	imms := int(immFromOperand(ops[2]))
+	imms := arm64Imm64(ops[2])
 	rd := arm64RegNum(operandRegName(ops[3]))
 	if rn < 0 || rd < 0 {
 		return nil, fmt.Errorf("invalid register operand in %s", mnem)
 	}
+	// The toolchain rejects bit numbers at or above the operand width, which
+	// sf (bit 31 of the base) selects: 64 when set, 32 otherwise.
+	width := uint32(32) << (baseOp >> 31 & 1)
+	if immr < 0 || uint32(immr) >= width || imms < 0 || uint32(imms) >= width {
+		return nil, fmt.Errorf("%s: bit number out of range (immr=%d imms=%d, width=%d)", mnem, immr, imms, width)
+	}
 	return a64wordLE(baseOp | uint32(immr)<<16 | uint32(imms)<<10 | uint32(rn)<<5 | uint32(rd)), nil
 }
 
@@ -1329,13 +1489,19 @@ func encodeARM64Extr(mnem string, baseOp uint32, ops []*ast.Operand) ([]byte, er
 	if len(ops) != 4 {
 		return nil, fmt.Errorf("%s expects 4 operands, got %d", mnem, len(ops))
 	}
-	lsb := int(immFromOperand(ops[0]))
+	lsb := arm64Imm64(ops[0])
 	rm := arm64RegNum(operandRegName(ops[1]))
 	rn := arm64RegNum(operandRegName(ops[2]))
 	rd := arm64RegNum(operandRegName(ops[3]))
 	if rm < 0 || rn < 0 || rd < 0 {
 		return nil, fmt.Errorf("invalid register operand in %s", mnem)
 	}
+	// The imms field is 6 bits and must stay below the operand width, which
+	// sf (bit 31 of the base) selects: 64 when set, 32 otherwise.
+	width := int64(32) << (baseOp >> 31 & 1)
+	if lsb < 0 || lsb >= width {
+		return nil, fmt.Errorf("%s: bit number %d out of range (width=%d)", mnem, lsb, width)
+	}
 	return a64wordLE(baseOp | uint32(rm)<<16 | uint32(lsb)<<10 | uint32(rn)<<5 | uint32(rd)), nil
 }
 
@@ -1367,7 +1533,7 @@ func AssembleFileARM64(f *ast.File) (*Image, error) {
 		return nil, err
 	}
 
-	img := &Image{Symbols: map[string]int{}}
+	img := &Image{Symbols: map[string]int{}, SourcePath: f.Path}
 	for _, d := range f.Decls {
 		t, ok := d.(*ast.Text)
 		if !ok {

asm/arm64_encode.go

@@ -27,6 +27,8 @@ package asm
 //	Uncond-branch   0x6B<<25 | opc<<21 | Rn<<5 | Rd   (BR/BLR/RET)
 //	ADR/ADRP        p<<31 | 0x10<<24 | immlo<<29 | immhi<<5 | Rd
 
+import "maps"
+
 // arm64RegNum returns the 5-bit register number for an AArch64 register name:
 // R0-R30 (integer), F0-F31 (floating point), and the ABI aliases the
 // runtime's assembly uses.  Returns -1 for an unrecognised name.
@@ -96,8 +98,12 @@ func arm64RegNum(name string) int {
 		return 30
 	case "R31", "ZR":
 		return 31
-	case "SP":
-		return 31 // SP and ZR share encoding 31; context determines meaning
+	case "SP", "RSP":
+		// RSP is the toolchain's spelling for register 31 (it rejects
+		// R31 in an operand); SP stays for sources that spell it the
+		// amd64 way.  SP and ZR share encoding 31; context determines
+		// the meaning.
+		return 31
 	}
 	// F0-F31.
 	if len(name) >= 1 && name[0] == 'F' {
@@ -262,19 +268,15 @@ type a64Format uint8
 
 const (
 	a64FDPSR         a64Format = iota // data-processing (shifted register): ADD, SUB, AND, ORR, EOR, etc.
-	a64FDPIR                          // data-processing (immediate): ADD/SUB $imm
-	a64FLogImm                        // logical (immediate): AND/ORR/EOR $imm
 	a64FMovWide                       // move wide: MOVZ, MOVN, MOVK
-	a64FLSU                           // load/store (unsigned immediate, scaled)
-	a64FLSUnscaled                    // load/store (unscaled immediate)
-	a64FLSPair                        // load/store pair
 	a64FBranch                        // unconditional branch (B/BL)
 	a64FBranchCond                    // conditional branch (B.cond)
 	a64FUncondBranch                  // unconditional branch register (BR/BLR/RET)
 	a64FADR                           // ADR/ADRP
 	a64FEXTR                          // EXTR
 	a64FBitfield                      // bitfield: BFI/BFXIL/SBFM/UBFM/BFM
-	a64FSystem                        // system: NOP, BRK, etc.
+	a64FShift                         // shifts: LSL/LSR/ASR alias SBFM/UBFM, ROR aliases EXTR; register forms are two-source
+	a64FDPR4                          // data-processing 4-register: MADD/MSUB, Ra in bits 14:10
 	a64FFP3                           // FP 3-operand (Rm, Rn, Rd): FADD, FSUB, FMUL, FDIV, etc.
 	a64FFPUnary                       // FP unary (Rn, Rd): FMOV, FABS, FNEG, FSQRT, FCVT, FRINT*
 	a64FFP4                           // FP 4-operand FMA (Ra, Rm, Rn, Rd): FMADD, FMSUB, etc.
@@ -282,10 +284,9 @@ const (
 	a64FFPCCmp                        // FP conditional compare (Rm, Rn, nzcv, cond): FCCMP, FCCMPE
 	a64FFPCvt                         // FP↔integer conversion: FCVTZS, SCVTF, etc.
 	a64FFPSel                         // FP conditional select (Rm, Rn, Rd, cond): FCSEL
-	a64FFMovGR                        // FMOV between GP and FP registers
 	a64FCRC32                         // CRC32
 	a64FCSEL                          // conditional select: CSEL, CSINC, CSINV, CSNEG
-	a64FExcl                          // exclusive load/store: LDXR, STXR, LDAXR, STLXR
+	a64FExcl                          // exclusive load/store: LDXR, STXR, LDAXR, STLXR and pair forms LDXP, STXP
 	a64FLSE                           // LSE atomics: LDADD, CAS, SWP
 	a64FSIMD3                         // SIMD 3-operand: VADD, VSUB, VMUL
 )
@@ -332,30 +333,14 @@ func init() {
 		"ANDSW": 0<<31 | 3<<29 | 0x0a<<24,
 		"BICS":  1<<31 | 3<<29 | 0x0a<<24 | 1<<21,
 		"BICSW": 0<<31 | 3<<29 | 0x0a<<24 | 1<<21,
-		// Shift
-		"LSL":  1<<31 | 0<<29 | 0x0a<<24, // alias of UBFM
-		"LSLW": 0<<31 | 0<<29 | 0x0a<<24,
-		"LSR":  1<<31 | 0<<29 | 0x0a<<24,
-		"LSRW": 0<<31 | 0<<29 | 0x0a<<24,
-		"ASR":  1<<31 | 0<<29 | 0x0a<<24,
-		"ASRW": 0<<31 | 0<<29 | 0x0a<<24,
-		"ROR":  1<<31 | 0<<29 | 0x0a<<24,
-		"RORW": 0<<31 | 0<<29 | 0x0a<<24,
-		// Multiply
-		"MADD":  1<<31 | 0<<29 | 0x1b<<24 | 0<<21,
-		"MADDW": 0<<31 | 0<<29 | 0x1b<<24 | 0<<21,
-		"MSUB":  1<<31 | 0<<29 | 0x1b<<24 | 1<<21,
-		"MSUBW": 0<<31 | 0<<29 | 0x1b<<24 | 1<<21,
-		// Divide
-		"SDIV":  1<<31 | 0<<29 | 0x0d<<24,
-		"SDIVW": 0<<31 | 0<<29 | 0x0d<<24,
-		"UDIV":  1<<31 | 0<<29 | 0x0d<<24 | 1<<10,
-		"UDIVW": 0<<31 | 0<<29 | 0x0d<<24 | 1<<10,
-		// CRC
-		"CRC32B": 0<<31 | 0<<29 | 0x1b<<24 | 4<<10,
-		"CRC32H": 0<<31 | 0<<29 | 0x1b<<24 | 5<<10,
-		"CRC32W": 0<<31 | 0<<29 | 0x1b<<24 | 6<<10,
-		"CRC32X": 1<<31 | 0<<29 | 0x1b<<24 | 7<<10,
+		// Divide (data-processing 2 source): the opcode occupies bits 15:10
+		// of the 0xd6<<21 fixed field, UDIV=0b0010 and SDIV=0b0011 (ARM ARM
+		// "Data-processing (2 source)"; the toolchain spells them OPDP2(2)
+		// and OPDP2(3)).  sf=1 selects the X forms.
+		"SDIV":  1<<31 | 0xd6<<21 | 3<<10,
+		"SDIVW": 0<<31 | 0xd6<<21 | 3<<10,
+		"UDIV":  1<<31 | 0xd6<<21 | 2<<10,
+		"UDIVW": 0<<31 | 0xd6<<21 | 2<<10,
 		// Conditional select
 		"CSEL":   1<<31 | 0<<29 | 0x1d<<24 | 0<<10,
 		"CSELW":  0<<31 | 0<<29 | 0x1d<<24 | 0<<10,
@@ -385,14 +370,37 @@ func init() {
 	a64InstrTable["MOV"] = a64Enc{format: a64FDPSR, op: dpsr["ORR"]}
 	a64InstrTable["MOVW"] = a64Enc{format: a64FDPSR, op: dpsr["ORRW"]}
 
-	// ---- data-processing (immediate) ----
-	// ADD/SUB $imm, Rn, Rd
-	a64InstrTable["ADDImm"] = a64Enc{format: a64FDPIR, op: 1<<31 | 0<<30 | 0<<29 | 0x11<<24}
-	a64InstrTable["ADDWImm"] = a64Enc{format: a64FDPIR, op: 0<<31 | 0<<30 | 0<<29 | 0x11<<24}
-	a64InstrTable["SUBImm"] = a64Enc{format: a64FDPIR, op: 1<<31 | 1<<30 | 0<<29 | 0x11<<24}
-	a64InstrTable["SUBWImm"] = a64Enc{format: a64FDPIR, op: 0<<31 | 1<<30 | 0<<29 | 0x11<<24}
-	a64InstrTable["ADDSImm"] = a64Enc{format: a64FDPIR, op: 1<<31 | 0<<30 | 1<<29 | 0x11<<24}
-	a64InstrTable["SUBSImm"] = a64Enc{format: a64FDPIR, op: 1<<31 | 1<<30 | 1<<29 | 0x11<<24}
+	// ---- shifts ----
+	// The mnemonic serves both forms: with an immediate the aliases of the
+	// data-processing (immediate) group apply (ARM ARM "Shifts"), with a
+	// register the data-processing (2 source) LSLV/LSRV/ASRV/RORV.  The op
+	// field carries the immediate-alias base; encodeARM64Shift derives both
+	// it and the two-source opcode.  Identities, W = 64 (X) or 32 (W):
+	//
+	//	LSL $sh, Rn, Rd = UBFM Rd, Rn, #(-sh) mod W, #(W-1)-sh
+	//	LSR $sh, Rn, Rd = UBFM Rd, Rn, #sh, #(W-1)
+	//	ASR $sh, Rn, Rd = SBFM Rd, Rn, #sh, #(W-1)
+	//	ROR $sh, Rn, Rd = EXTR Rd, Rn, Rn, #sh
+	shifts := map[string]a64Enc{
+		"LSL":  {format: a64FShift, op: 1<<31 | 2<<29 | 0x26<<23 | 1<<22}, // UBFM X
+		"LSLW": {format: a64FShift, op: 0<<31 | 2<<29 | 0x26<<23 | 0<<22}, // UBFM W
+		"LSR":  {format: a64FShift, op: 1<<31 | 2<<29 | 0x26<<23 | 1<<22}, // UBFM X
+		"LSRW": {format: a64FShift, op: 0<<31 | 2<<29 | 0x26<<23 | 0<<22}, // UBFM W
+		"ASR":  {format: a64FShift, op: 1<<31 | 0<<29 | 0x26<<23 | 1<<22}, // SBFM X
+		"ASRW": {format: a64FShift, op: 0<<31 | 0<<29 | 0x26<<23 | 0<<22}, // SBFM W
+		"ROR":  {format: a64FShift, op: 1<<31 | 0x27<<23 | 1<<22},         // EXTR X
+		"RORW": {format: a64FShift, op: 0<<31 | 0x27<<23 | 0<<22},         // EXTR W
+	}
+	maps.Copy(a64InstrTable, shifts)
+
+	// ---- multiply accumulate ----
+	// MADD/MSUB Rm, Ra, Rn, Rd: sf 00 11011 o0(15) Rm Ra Rn Rd.  The
+	// toolchain's optab has no shorter row, so all four operands are
+	// mandatory, and Ra is the SECOND operand.
+	a64InstrTable["MADD"] = a64Enc{format: a64FDPR4, op: 1<<31 | 0x1b<<24}
+	a64InstrTable["MADDW"] = a64Enc{format: a64FDPR4, op: 0<<31 | 0x1b<<24}
+	a64InstrTable["MSUB"] = a64Enc{format: a64FDPR4, op: 1<<31 | 0x1b<<24 | 1<<15}
+	a64InstrTable["MSUBW"] = a64Enc{format: a64FDPR4, op: 0<<31 | 0x1b<<24 | 1<<15}
 
 	// ---- move wide ----
 	// MOVZ/MOVN/MOVK
@@ -407,22 +415,9 @@ func init() {
 	a64InstrTable["ADR"] = a64Enc{format: a64FADR, op: 0}
 	a64InstrTable["ADRP"] = a64Enc{format: a64FADR, op: 1}
 
-	// ---- load/store (unsigned immediate) ----
-	a64InstrTable["MOVD"] = a64Enc{format: a64FLSU, op: 3<<30 | 7<<27 | 1<<22}          // LDR 64-bit
-	a64InstrTable["MOVWU"] = a64Enc{format: a64FLSU, op: 2<<30 | 7<<27 | 1<<22}         // LDR 32-bit unsigned
-	a64InstrTable["MOVHU"] = a64Enc{format: a64FLSU, op: 1<<30 | 7<<27 | 1<<22}         // LDRH unsigned
-	a64InstrTable["MOVBU"] = a64Enc{format: a64FLSU, op: 0<<30 | 7<<27 | 1<<22}         // LDRB unsigned
-	a64InstrTable["MOVW"] = a64Enc{format: a64FLSU, op: 2<<30 | 7<<27 | 2<<22}          // LDRSW (signed 32→64)
-	a64InstrTable["MOVH"] = a64Enc{format: a64FLSU, op: 1<<30 | 7<<27 | 2<<22}          // LDRSH (signed half)
-	a64InstrTable["MOVB"] = a64Enc{format: a64FLSU, op: 0<<30 | 7<<27 | 2<<22}          // LDRSB (signed byte)
-	a64InstrTable["FMOVS"] = a64Enc{format: a64FLSU, op: 2<<30 | 7<<27 | 1<<26 | 1<<22} // FLDR 32-bit FP
-	a64InstrTable["FMOVD"] = a64Enc{format: a64FLSU, op: 3<<30 | 7<<27 | 1<<26 | 1<<22} // FLDR 64-bit FP
-
-	// Store opcodes (load ^ (1<<22)):
-	// STR 64-bit: size=3, V=0, opc=00 → 3<<30 | 7<<27 | 0<<22
-	// STR 32-bit: size=2, V=0, opc=00 → 2<<30 | 7<<27 | 0<<22
-	// STRH:      size=1, V=0, opc=00 → 1<<30 | 7<<27 | 0<<22
-	// STRB:      size=0, V=0, opc=00 → 0<<30 | 7<<27 | 0<<22
+	// Load/store mnemonics never enter this table: the MOV pseudo-instruction
+	// dispatch handles them through a64LoadTable, which also carries the store
+	// opcode (integer and FP stores both use opc=00, differing only in V).
 
 	// ---- branches ----
 	a64InstrTable["B"] = a64Enc{format: a64FBranch, op: 0<<31 | 5<<26}
@@ -445,10 +440,8 @@ func init() {
 	a64InstrTable["RET"] = a64Enc{format: a64FUncondBranch, op: 0x6B<<25 | 2<<21}
 
 	// ---- system ----
-	a64InstrTable["NOP"] = a64Enc{format: a64FSystem, op: a64NOP}
-	a64InstrTable["NOOP"] = a64Enc{format: a64FSystem, op: a64NOP}
-	a64InstrTable["BRK"] = a64Enc{format: a64FSystem, op: 0xd4200000}
-	a64InstrTable["UNDEF"] = a64Enc{format: a64FSystem, op: a64BRK(0)}
+	// NOP/NOOP/UNDEF are spelled out in encodeARM64Instr's pseudo switch,
+	// so they carry no table entry; a64NOP and a64BRK are the encoders.
 
 	// ---- EXTR ----
 	a64InstrTable["EXTR"] = a64Enc{format: a64FEXTR, op: 1<<31 | 0x27<<23 | 1<<22}
@@ -549,8 +542,8 @@ func init() {
 		a64InstrTable[m] = a64Enc{format: a64FFPCvt, op: op}
 	}
 
-	// ---- FMOV between GP and FP registers ----
-	a64InstrTable["FMOVGR"] = a64Enc{format: a64FFMovGR, op: 0x1e260000} // placeholder, actual encoding depends on direction
+	// FMOV between GP and FP registers needs no table entry: the MOV
+	// pseudo-instruction dispatches it by operand class (encodeARM64RegMove).
 
 	// ---- conditional select: CSEL, CSINC, CSINV, CSNEG ----
 	csel := map[string]uint32{
@@ -586,6 +579,10 @@ func init() {
 	}
 
 	// ---- exclusive load/store ----
+	// Single-register forms pre-set the unused Rs and Rt2 fields to 31 (the
+	// 0x7c00/0x1f0000 halves of the constants below); the register-pair
+	// forms carry a real Rt2 in bits 14:10, so their opcodes pre-set
+	// neither field.
 	a64InstrTable["LDXR"] = a64Enc{format: a64FExcl, op: 0xc85f7c00}
 	a64InstrTable["LDXRB"] = a64Enc{format: a64FExcl, op: 0x085f7c00}
 	a64InstrTable["LDXRH"] = a64Enc{format: a64FExcl, op: 0x485f7c00}
@@ -594,6 +591,12 @@ func init() {
 	a64InstrTable["LDAXRB"] = a64Enc{format: a64FExcl, op: 0x085ffc00}
 	a64InstrTable["LDAXRH"] = a64Enc{format: a64FExcl, op: 0x485ffc00}
 	a64InstrTable["LDAXRW"] = a64Enc{format: a64FExcl, op: 0x885ffc00}
+	// Pair loads, LDSTX(sz, 0, l=1, o1=1, o0) in asm7.go: LDXP/ LDXPW have
+	// o0=0, LDAXP/LDAXPW o0=1 (bit 15).  Rs (bits 20:16) stays 31.
+	a64InstrTable["LDXP"] = a64Enc{format: a64FExcl, op: 0xc8600000}
+	a64InstrTable["LDXPW"] = a64Enc{format: a64FExcl, op: 0x88600000}
+	a64InstrTable["LDAXP"] = a64Enc{format: a64FExcl, op: 0xc8608000}
+	a64InstrTable["LDAXPW"] = a64Enc{format: a64FExcl, op: 0x88608000}
 	a64InstrTable["STXR"] = a64Enc{format: a64FExcl, op: 0xc8007c00}
 	a64InstrTable["STXRB"] = a64Enc{format: a64FExcl, op: 0x08007c00}
 	a64InstrTable["STXRH"] = a64Enc{format: a64FExcl, op: 0x48007c00}
@@ -602,6 +605,12 @@ func init() {
 	a64InstrTable["STLXRB"] = a64Enc{format: a64FExcl, op: 0x0800fc00}
 	a64InstrTable["STLXRH"] = a64Enc{format: a64FExcl, op: 0x4800fc00}
 	a64InstrTable["STLXRW"] = a64Enc{format: a64FExcl, op: 0x8800fc00}
+	// Pair stores, LDSTX(sz, 0, l=0, o1=1, o0): STXP/STXPW have o0=0,
+	// STLXP/STLXPW o0=1 (bit 15).  Both Rs and Rt2 are real fields.
+	a64InstrTable["STXP"] = a64Enc{format: a64FExcl, op: 0xc8200000}
+	a64InstrTable["STXPW"] = a64Enc{format: a64FExcl, op: 0x88200000}
+	a64InstrTable["STLXP"] = a64Enc{format: a64FExcl, op: 0xc8208000}
+	a64InstrTable["STLXPW"] = a64Enc{format: a64FExcl, op: 0x88208000}
 
 	// ---- LSE atomics ----
 	a64InstrTable["LDADDD"] = a64Enc{format: a64FLSE, op: 3<<30 | 0x1c1<<21 | 0x00<<10}
@@ -642,14 +651,11 @@ var a64LoadTable = map[string]a64LSType{
 	"FMOVD": {3, 1, 1}, // LDR D (64-bit FP)
 }
 
-// a64StoreOpc returns the store opc for a given load type.
-// For integer: store opc = 00 (the load opc bits cleared).
-// For FP: store opc = 00 (same pattern).
+// a64StoreOpc returns the store opc for a given load type: integer and FP
+// stores both encode opc=00 (the load's signedness bit sits in opc[1], which
+// the store form clears; FP registers are selected by V, not opc).
 func a64StoreOpc(t a64LSType) int {
-	if t.V == 1 {
-		return 0 // FP store
-	}
-	return 0 // integer store
+	return 0
 }
 
 // arm64RegClass discriminates integer (R), floating-point (F) registers for

asm/arm64_encode_test.go

@@ -611,3 +611,380 @@ TEXT ·f(SB), NOSPLIT, $0-0
 		}
 	}
 }
+
+// arm64Words assembles a single NOSPLIT leaf body and returns its words.
+func arm64Words(t *testing.T, body string) []uint32 {
+	t.Helper()
+	f, errs := parser.Parse("test_arm64.s", "#include \"textflag.h\"\n\nTEXT ·f(SB), NOSPLIT, $0-0\n"+body+"\tRET\n")
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFileARM64(f)
+	if err != nil {
+		t.Fatalf("AssembleFileARM64: %v", err)
+	}
+	return leWords(img.Code)
+}
+
+// TestArm64ShiftEncodings pins the shift words against `go tool asm -S`
+// output (Go 1.27, arm64): immediate forms alias SBFM/UBFM with ROR as EXTR,
+// register forms are the two-source LSLV/LSRV/ASRV/RORV.
+func TestArm64ShiftEncodings(t *testing.T) {
+	got := arm64Words(t, "\tLSL $4, R0, R1\n\tLSR $8, R0, R2\n\tASR $4, R0, R3\n\tROR $12, R0, R4\n"+
+		"\tLSLW $4, R0, R5\n\tLSRW $8, R0, R6\n\tASRW $4, R0, R7\n\tRORW $12, R0, R8\n")
+	want := []uint32{
+		0xd37cec01, // LSL $4  = UBFM X1, X0, #60, #59
+		0xd348fc02, // LSR $8  = UBFM X2, X0, #8, #63
+		0x9344fc03, // ASR $4  = SBFM X3, X0, #4, #63
+		0x93c03004, // ROR $12 = EXTR X4, X0, X0, #12
+		0x531c6c05, // LSLW $4 = UBFM W5, W0, #28, #27
+		0x53087c06, // LSRW $8 = UBFM W6, W0, #8, #31
+		0x13047c07, // ASRW $4 = SBFM W7, W0, #4, #31
+		0x13803008, // RORW $12 = EXTR W8, W0, W0, #12
+		0xd65f03c0, // RET
+	}
+	if len(got) != len(want) {
+		t.Fatalf("word count = %d, want %d", len(got), len(want))
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			t.Errorf("imm shift word %d = %08x, want %08x", i, got[i], want[i])
+		}
+	}
+
+	got = arm64Words(t, "\tLSL R9, R0, R10\n\tLSR R9, R0, R11\n\tASR R9, R0, R12\n\tROR R9, R0, R13\n"+
+		"\tLSLW R9, R0, R14\n\tLSRW R9, R0, R15\n\tASRW R9, R0, R16\n\tRORW R9, R0, R17\n")
+	want = []uint32{
+		0x9ac9200a, // LSLV X10, X0, X9
+		0x9ac9240b, // LSRV X11, X0, X9
+		0x9ac9280c, // ASRV X12, X0, X9
+		0x9ac92c0d, // RORV X13, X0, X9
+		0x1ac9200e, // LSLV W14, W0, W9
+		0x1ac9240f, // LSRV W15, W0, W9
+		0x1ac92810, // ASRV W16, W0, W9
+		0x1ac92c11, // RORV W17, W0, W9
+		0xd65f03c0, // RET
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			t.Errorf("reg shift word %d = %08x, want %08x", i, got[i], want[i])
+		}
+	}
+
+	// Two-operand spellings fold to Rn = Rd.
+	got = arm64Words(t, "\tLSL $4, R1\n\tLSR R9, R1\n\tASR $4, R1\n\tROR R9, R1\n\tLSLW $4, R1\n\tRORW R9, R1\n")
+	want = []uint32{
+		0xd37cec21, // LSL $4, R1 = UBFM X1, X1, #60, #59
+		0x9ac92421, // LSRV X1, X1, X9
+		0x9344fc21, // ASR $4, R1 = SBFM X1, X1, #4, #63
+		0x9ac92c21, // RORV X1, X1, X9
+		0x531c6c21, // LSLW $4, R1 = UBFM W1, W1, #28, #27
+		0x1ac92c21, // RORV W1, W1, W9
+		0xd65f03c0, // RET
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			t.Errorf("2op shift word %d = %08x, want %08x", i, got[i], want[i])
+		}
+	}
+}
+
+// TestArm64ShiftRangeErrors: the toolchain reports "illegal bit number" for
+// shift amounts at or above the operand width.
+func TestArm64ShiftRangeErrors(t *testing.T) {
+	for _, src := range []string{
+		"\tLSL $64, R0, R1\n",
+		"\tLSRW $32, R0, R1\n",
+		"\tRORW $32, R0, R1\n",
+		"\tASR $-1, R0, R1\n",
+	} {
+		f, errs := parser.Parse("test_arm64.s", "#include \"textflag.h\"\n\nTEXT ·f(SB), NOSPLIT, $0-0\n"+src+"\tRET\n")
+		if len(errs) > 0 {
+			t.Fatalf("parse: %v", errs)
+		}
+		if _, err := AssembleFileARM64(f); err == nil {
+			t.Errorf("%s: expected an error, got none", src)
+		}
+	}
+}
+
+// TestArm64DivEncodings pins SDIV/UDIV in both widths: the 2-source opcode
+// field (bits 15:10 of the 0xd6<<21 fixed field) is UDIV=0b0010, SDIV=0b0011.
+func TestArm64DivEncodings(t *testing.T) {
+	got := arm64Words(t, "\tSDIV R1, R2, R3\n\tUDIV R1, R2, R3\n\tSDIVW R1, R2, R3\n\tUDIVW R1, R2, R3\n")
+	want := []uint32{
+		0x9ac10c43, // SDIV X3, X2, X1
+		0x9ac10843, // UDIV X3, X2, X1
+		0x1ac10c43, // SDIV W3, W2, W1
+		0x1ac10843, // UDIV W3, W2, W1
+		0xd65f03c0, // RET
+	}
+	if len(got) != len(want) {
+		t.Fatalf("word count = %d, want %d", len(got), len(want))
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			t.Errorf("div word %d = %08x, want %08x", i, got[i], want[i])
+		}
+	}
+}
+
+// TestArm64MAddSub pins the four-operand MADD/MSUB words (Rm, Ra, Rn, Rd,
+// with Ra in bits 14:10) and rejects the shorter spellings the toolchain
+// also rejects.
+func TestArm64MAddSub(t *testing.T) {
+	got := arm64Words(t, "\tMADD R1, R2, R3, R4\n\tMSUB R1, R2, R3, R4\n\tMADDW R1, R2, R3, R5\n\tMSUBW R1, R2, R3, R5\n")
+	want := []uint32{
+		0x9b010864, // MADD X4, X3, X1, X2 (Rm=1, Ra=2, Rn=3)
+		0x9b018864, // MSUB X4, X3, X1, X2
+		0x1b010865, // MADD W5, W3, W1, W2
+		0x1b018865, // MSUB W5, W3, W1, W2
+		0xd65f03c0, // RET
+	}
+	if len(got) != len(want) {
+		t.Fatalf("word count = %d, want %d", len(got), len(want))
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			t.Errorf("madd word %d = %08x, want %08x", i, got[i], want[i])
+		}
+	}
+
+	// The accumulate operand is mandatory: 2- and 3-operand forms error
+	// rather than silently reading R0 or ZR as the accumulator.
+	for _, body := range []string{
+		"\tMADD R1, R2\n",
+		"\tMADD R1, R2, R3\n",
+		"\tMSUBW R1, R2, R3\n",
+	} {
+		f, errs := parser.Parse("test_arm64.s", "#include \"textflag.h\"\n\nTEXT ·f(SB), NOSPLIT, $0-0\n"+body+"\tRET\n")
+		if len(errs) > 0 {
+			t.Fatalf("parse: %v", errs)
+		}
+		if _, err := AssembleFileARM64(f); err == nil {
+			t.Errorf("%s: expected an error, got none", body)
+		}
+	}
+}
+
+// TestArm64MovImmWidth pins the immediate classifications whose size pass
+// once disagreed with the encoder: negative and 0xFFFFFFFF W values go
+// through MOVN after 32-bit truncation, and 3- to 4-chunk constants expand
+// to one word per non-zero chunk.
+func TestArm64MovImmWidth(t *testing.T) {
+	got := arm64Words(t, "\tMOVW $-1, R0\n\tMOVW $0xFFFFFFFF, R3\n")
+	want := []uint32{
+		0x12800000, // MOVN W0, #0
+		0x12800003, // MOVN W3, #0
+		0xd65f03c0, // RET
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			t.Errorf("movw word %d = %08x, want %08x", i, got[i], want[i])
+		}
+	}
+
+	for _, tt := range []struct {
+		body  string
+		words int
+	}{
+		{"\tMOVD $0x0001000200030000, R2\n", 3}, // three chunks
+		{"\tMOVD $0x0001000200030004, R1\n", 4}, // four chunks
+		{"\tMOVW $-1, R0\n", 1},                 // MOVN after truncation
+	} {
+		if got := arm64Words(t, tt.body); len(got) != tt.words+1 {
+			t.Errorf("%s: %d words, want %d (including RET)", tt.body, len(got), tt.words+1)
+		}
+	}
+}
+
+// TestArm64ExclOffsetErrors: exclusive and atomic encodings carry no
+// immediate field, so a non-zero offset is rejected the way the toolchain
+// reports "illegal combination" for it, never silently dropped.
+func TestArm64ExclOffsetErrors(t *testing.T) {
+	for _, body := range []string{
+		"\tLDXR 8(R1), R2\n",
+		"\tLDAXR 8(R1), R2\n",
+		"\tSTXR R3, 8(R1), R4\n",
+		"\tSTLXR R3, 8(R1), R4\n",
+		"\tCASD R3, 8(R1), R4\n",
+		"\tLDADDD R3, 8(R1), R4\n",
+	} {
+		f, errs := parser.Parse("test_arm64.s", "#include \"textflag.h\"\n\nTEXT ·f(SB), NOSPLIT, $0-0\n"+body+"\tRET\n")
+		if len(errs) > 0 {
+			t.Fatalf("parse: %v", errs)
+		}
+		if _, err := AssembleFileARM64(f); err == nil {
+			t.Errorf("%s: expected an error, got none", body)
+		}
+	}
+}
+
+// TestArm64ExclNoOffset pins the plain (Rn) forms, byte-for-byte against
+// go tool asm.  The toolchain parses the FIRST register of a store as the
+// data register and the LAST as the status register (asm7.go case 59), and
+// the pair forms as (Rt1, Rt2) (case 58/59):
+//
+//	STXR R3, (R1), R4         → c8047c23 (Rt=3, Rn=1, Rs=4)
+//	STXP (R3, R4), (R1), R5   → c8251023 (Rt=3, Rt2=4, Rn=1, Rs=5)
+//	LDXP (R1), (R3, R4)       → c87f1023 (Rn=1, Rt=3, Rt2=4)
+func TestArm64ExclNoOffset(t *testing.T) {
+	got := arm64Words(t, "\tLDXR (R1), R2\n\tSTXR R3, (R1), R4\n"+
+		"\tSTXP (R3, R4), (R1), R5\n\tSTXPW (R3, R4), (R1), R5\n"+
+		"\tLDXP (R1), (R3, R4)\n\tLDXPW (R1), (R3, R4)\n"+
+		"\tSTXR R3, (RSP), R4\n\tLDXR (RSP), R2\n")
+	want := []uint32{
+		0xc85f7c22, // LDXR X2, [X1]
+		0xc8047c23, // STXR W3, [X1], W4 with Rt = R3, Rs = R4
+		0xc8251023, // STXP (R3, R4), [X1], R5
+		0x88251023, // STXPW (R3, R4), [X1], R5
+		0xc87f1023, // LDXP [X1], (R3, R4)
+		0x887f1023, // LDXPW [X1], (R3, R4)
+		0xc8047fe3, // STXR R3, [SP], R4
+		0xc85f7fe2, // LDXR [SP], R2
+		0xd65f03c0, // RET
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			t.Errorf("excl word %d = %08x, want %08x", i, got[i], want[i])
+		}
+	}
+}
+
+// TestArm64AddSubImmRange: immediates that cannot ride the imm12 field are
+// rejected instead of wrapping through int32.
+func TestArm64AddSubImmRange(t *testing.T) {
+	for _, body := range []string{
+		"\tADD $0x100000000, R0, R1\n",
+		"\tSUB $-0x100000000, R0, R1\n",
+		"\tCMP $0x100000000, R0\n",
+	} {
+		f, errs := parser.Parse("test_arm64.s", "#include \"textflag.h\"\n\nTEXT ·f(SB), NOSPLIT, $0-0\n"+body+"\tRET\n")
+		if len(errs) > 0 {
+			t.Fatalf("parse: %v", errs)
+		}
+		if _, err := AssembleFileARM64(f); err == nil {
+			t.Errorf("%s: expected an error, got none", body)
+		}
+	}
+}
+
+// TestArm64LargeRegisterOffset pins the large-offset path for a register
+// base: the ADD offsets from the operand's own base, not from SP, matching
+// the toolchain's `ADD $(256<<12), R2, R27; MOVD (R27), R3`.
+func TestArm64LargeRegisterOffset(t *testing.T) {
+	got := arm64Words(t, "\tMOVD 0x100000(R2), R3\n\tMOVD R3, 0x100000(R2)\n")
+	want := []uint32{
+		0x9144005b, // ADD $(256<<12), R2, R27
+		0xf9400363, // MOVD (R27), R3
+		0x9144005b, // ADD $(256<<12), R2, R27
+		0xf9000363, // MOVD R3, (R27)
+		0xd65f03c0, // RET
+	}
+	if len(got) != len(want) {
+		t.Fatalf("word count = %d, want %d", len(got), len(want))
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			t.Errorf("large offset word %d = %08x, want %08x", i, got[i], want[i])
+		}
+	}
+}
+
+// TestArm64LargeFrameSpadj checks the stack-adjustment boundaries of a frame
+// whose autosize must be materialised into REGTMP: $5000 rounds the autosize
+// to 5024, so the prologue is [MOVD $5024, R27][SUB R27, RSP, R20][STP][ADD
+// R20, SP][SUB $8] and SP moves only at its fourth word, while the RET's
+// epilogue is [LDP][MOVD $5024, R27][ADD R27, RSP, RSP] before the final
+// RET.  These PCs feed the DWARF CFA rules and the goobj stack maps.
+func TestArm64LargeFrameSpadj(t *testing.T) {
+	f, errs := parser.Parse("frame_arm64.s", "#include \"textflag.h\"\n\nTEXT ·framed(SB), $5000-0\n\tCALL ·other(SB)\n\tRET\n\nTEXT ·other(SB), NOSPLIT, $0\n\tRET\n")
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFileARM64(f)
+	if err != nil {
+		t.Fatalf("AssembleFileARM64: %v", err)
+	}
+	fn := img.Funcs[0]
+	// autosize 5024: class-2 guard of 6 words (24 bytes), a 5-word prologue
+	// whose ADD R20, SP sits at byte 8 inside it, a one-instruction body,
+	// then a 3-word epilogue before the final RET.
+	wantSpadj := []SpadjStep{{PC: 24 + 12, Value: 5024}, {PC: 24 + 20 + 4 + 12, Value: 0}}
+	if len(fn.Spadj) != len(wantSpadj) {
+		t.Fatalf("spadj = %v, want %v", fn.Spadj, wantSpadj)
+	}
+	for i := range wantSpadj {
+		if fn.Spadj[i] != wantSpadj[i] {
+			t.Errorf("spadj[%d] = %v, want %v", i, fn.Spadj[i], wantSpadj[i])
+		}
+	}
+	// The words those PCs point between: the prologue's ADD R20, SP at byte
+	// 36, and the epilogue's materialised ADD R27, RSP, RSP right before the
+	// final RET at byte 60.
+	words := leWords(img.Code[fn.Offset : fn.Offset+fn.Size])
+	if got := words[(24+12)/4]; got != 0x9100029f {
+		t.Errorf("prologue word at byte 36 = %08x, want 9100029f (ADD R20, SP)", got)
+	}
+	if got := words[(24+20+4+8)/4]; got != 0x8b3b63ff {
+		t.Errorf("epilogue word at byte 56 = %08x, want 8b3b63ff (ADD R27, RSP, RSP)", got)
+	}
+	if got := words[(24+20+4+12)/4]; got != 0xd65f03c0 {
+		t.Errorf("final RET word at byte 60 = %08x, want d65f03c0", got)
+	}
+}
+
+// TestArm64SplitFrameSpadj pins the addcon2 band, where neither imm12 form
+// nor a single MOVZ carries the autosize and the toolchain splits the
+// prologue SUB into two imm12 instructions (asm7.go case 48) while the
+// non-leaf RET still materialises the value into REGTMP (obj7.go ARET,
+// issue 73259).  $65664 rounds the autosize to 65680 = 144 + 16<<12:
+//
+//	[SUB $144, RSP, R20][SUB $(16<<12), R20, R20][STP][MOVD R20, SP][SUB $8]
+//	[CALL]
+//	[LDP][MOVD $144, R27][MOVK $(1<<16), R27][ADD R27, RSP, RSP][RET]
+//
+// SP moves at the fourth word (byte 12) and returns to zero at the final
+// RET (byte 40); the words are go tool asm's own for the same source.
+func TestArm64SplitFrameSpadj(t *testing.T) {
+	f, errs := parser.Parse("frame_arm64.s", "#include \"textflag.h\"\n\nTEXT ·framed(SB), NOSPLIT, $65664-0\n\tCALL ·other(SB)\n\tRET\n\nTEXT ·other(SB), NOSPLIT, $0\n\tRET\n")
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFileARM64(f)
+	if err != nil {
+		t.Fatalf("AssembleFileARM64: %v", err)
+	}
+	fn := img.Funcs[0]
+	wantSpadj := []SpadjStep{{PC: 12, Value: 65680}, {PC: 40, Value: 0}}
+	if len(fn.Spadj) != len(wantSpadj) {
+		t.Fatalf("spadj = %v, want %v", fn.Spadj, wantSpadj)
+	}
+	for i := range wantSpadj {
+		if fn.Spadj[i] != wantSpadj[i] {
+			t.Errorf("spadj[%d] = %v, want %v", i, fn.Spadj[i], wantSpadj[i])
+		}
+	}
+	want := []uint32{
+		0xd10243f4, // SUB $144, RSP, R20
+		0xd1404294, // SUB $(16<<12), R20, R20
+		0xa93ffa9d, // STP (R29, R30), -8(R20)
+		0x9100029f, // MOVD R20, RSP
+		0xd10023fd, // SUB $8, RSP, R29
+		0x94000000, // CALL (relocation masked at link time)
+		0xa97ffbfd, // LDP -8(RSP), (R29, R30)
+		0xd280121b, // MOVD $144, R27
+		0xf2a0003b, // MOVK $(1<<16), R27
+		0x8b3b63ff, // ADD R27, RSP, RSP
+		0xd65f03c0, // RET
+	}
+	words := leWords(img.Code[fn.Offset : fn.Offset+fn.Size])
+	if len(words) != len(want) {
+		t.Fatalf("framed = %d words, want %d", len(words), len(want))
+	}
+	for i, w := range want {
+		if words[i] != w {
+			t.Errorf("word %d = %08x, want %08x", i, words[i], w)
+		}
+	}
+}

asm/arm64_frame.go

@@ -187,10 +187,32 @@ func arm64Prologue(fi arm64FrameInfo) []byte {
 	return a64WordsLE(ws...)
 }
 
-// arm64SubImmWords emits SUB $imm, SP, Rd: the immediate form when the value
-// fits the imm12 field (plain, or shifted left by 12 when it is a multiple
-// of 4096); otherwise the toolchain materialises it into REGTMP (R27) and
-// subtracts the register in the extended-register form.
+// arm64SplitImm12 reports whether the toolchain decomposes ADD/SUB $imm into
+// two imm12 instructions instead of materialising it into REGTMP
+// (asm7.go case 48, the C_ADDCON2 class): the value must fit 24 bits
+// unsigned and be neither encodable as one imm12 (checked by the callers
+// first), nor loadable into a register in a single MOVZ/MOVN word, nor a
+// logical immediate, because conclass tests all three before C_ADDCON2.
+func arm64SplitImm12(imm uint32) bool {
+	if imm > 0xFFFFFF {
+		return false
+	}
+	if _, _, _, ok := arm64Bitmask(uint64(imm), 1); ok {
+		return false
+	}
+	return arm64Movcon(int64(imm)) < 0 && arm64Movcon(^int64(imm)) < 0
+}
+
+// arm64SubImmWords emits SUB $imm, SP, Rd with the toolchain's ladder for an
+// ADD/SUB constant (asm7.go conclass and cases 2, 48, 62 and 13): the
+// immediate form when the value fits imm12 (plain, or shifted left by 12
+// when it is a multiple of 4096); a value with a single 16-bit chunk, a
+// logical immediate, or one wider than 24 bits is materialised into REGTMP
+// (R27) and subtracted in the extended-register form; everything else up to
+// 0xFFFFFF is split into two imm12 instructions:
+//
+//	SUB $(imm&0xfff), SP, Rd
+//	SUB $((imm&0xfff000)>>12)<<12, Rd, Rd
 func arm64SubImmWords(imm uint32, rd uint32) []uint32 {
 	if imm <= 0xFFF {
 		return []uint32{a64AddSub(1, 1, 0, 0, imm, 31, rd)}
@@ -198,15 +220,21 @@ func arm64SubImmWords(imm uint32, rd uint32) []uint32 {
 	if imm <= 4095<<12 && imm&0xFFF == 0 {
 		return []uint32{a64AddSub(1, 1, 0, 1, imm>>12, 31, rd)}
 	}
-	mov, err := encodeARM64LoadImm(27, int64(imm), "MOVD")
-	if err != nil {
-		mov = nil
+	if !arm64SplitImm12(imm) {
+		mov, err := encodeARM64LoadImm(27, int64(imm), "MOVD")
+		if err != nil {
+			mov = nil
+		}
+		return append(wordsOf(mov), arm64DPExtWords(arm64OpSub, 27, 31, rd))
+	}
+	return []uint32{
+		a64AddSub(1, 1, 0, 0, imm&0xFFF, 31, rd),
+		a64AddSub(1, 1, 0, 1, (imm&0xFFF000)>>12, rd, rd),
 	}
-	return append(wordsOf(mov), arm64DPExtWords(arm64OpSub, 27, 31, rd))
 }
 
-// arm64AddImmWords emits ADD $imm, SP, Rd with the same imm12, shifted-imm12
-// and REGTMP fallback ladder.
+// arm64AddImmWords emits ADD $imm, SP, Rd with the same imm12, shifted-imm12,
+// split and REGTMP ladder as arm64SubImmWords.
 func arm64AddImmWords(imm uint32, rd uint32) []uint32 {
 	if imm <= 0xFFF {
 		return []uint32{a64AddSub(1, 0, 0, 0, imm, 31, rd)}
@@ -214,11 +242,35 @@ func arm64AddImmWords(imm uint32, rd uint32) []uint32 {
 	if imm <= 4095<<12 && imm&0xFFF == 0 {
 		return []uint32{a64AddSub(1, 0, 0, 1, imm>>12, 31, rd)}
 	}
-	mov, err := encodeARM64LoadImm(27, int64(imm), "MOVD")
+	if !arm64SplitImm12(imm) {
+		mov, err := encodeARM64LoadImm(27, int64(imm), "MOVD")
+		if err != nil {
+			mov = nil
+		}
+		return append(wordsOf(mov), arm64DPExtWords(arm64OpAdd, 27, 31, rd))
+	}
+	return []uint32{
+		a64AddSub(1, 0, 0, 0, imm&0xFFF, 31, rd),
+		a64AddSub(1, 0, 0, 1, (imm&0xFFF000)>>12, rd, rd),
+	}
+}
+
+// arm64RetAddWords emits the frame deallocation of a non-leaf RET with a
+// large frame.  The toolchain adds the frame back with a single instruction:
+// a plain imm12 ADD when autosize fits 12 bits, otherwise the value is
+// materialised into REGTMP and added as a register, so the epilogue never
+// leaves a partially deallocated frame (obj7.go ARET, issue 73259).  The
+// shifted-imm12 and split-imm12 forms are therefore never used here, unlike
+// the leaf epilogue's plain ADD instructions.
+func arm64RetAddWords(autosize uint32) []uint32 {
+	if autosize < 1<<12 {
+		return []uint32{a64AddSub(1, 0, 0, 0, autosize, 31, 31)}
+	}
+	mov, err := encodeARM64LoadImm(27, int64(autosize), "MOVD")
 	if err != nil {
 		mov = nil
 	}
-	return append(wordsOf(mov), arm64DPExtWords(arm64OpAdd, 27, 31, rd))
+	return append(wordsOf(mov), arm64DPExtWords(arm64OpAdd, 27, 31, 31))
 }
 
 // arm64Return returns the bytes for a RET: the epilogue (restore FP/LR and
@@ -237,11 +289,11 @@ func arm64Return(fi arm64FrameInfo) []byte {
 				arm64PostLoad(3, 0, int32(fi.autosize), 31, 30), // LDR.P LR, [SP], #autosize
 			)
 		} else {
-			// Large frame: LDP -8(SP), (FP, LR); ADD $autosize, SP, SP
+			// Large frame: LDP -8(SP), (FP, LR), then deallocate.
 			ws = append(ws,
 				a64LSP(2, 0, 1, -1, 30, 31, 29), // LDP FP, LR, [SP, #-8] (opc=2 for 64-bit pair)
 			)
-			ws = append(ws, arm64AddImmWords(uint32(fi.autosize), 31)...)
+			ws = append(ws, arm64RetAddWords(uint32(fi.autosize))...)
 		}
 	}
 	// RET: BR LR (0xd65f03c0)
@@ -258,22 +310,32 @@ func arm64PrologueSpadjPC(fi arm64FrameInfo) int {
 	if fi.autosize <= 0xf0 {
 		return 4 // MOVD.W instruction decrements SP
 	}
-	return 8 // SUB + STP + MOVD (3 instructions, SP updated at the MOVD)
+	// Large frame: [SUB words][STP][ADD R20, SP]; SP moves at the ADD, whose
+	// position depends on how many words the SUB itself took (immediate,
+	// shifted immediate, the two-word imm12 split, or a materialised REGTMP
+	// sequence).
+	return 4 * (len(arm64SubImmWords(uint32(fi.autosize), 20)) + 1)
 }
 
 // arm64ReturnEpilogueLen returns the byte length of the RET's epilogue up to
-// (but not including) the final RET instruction.
+// (but not including) the final RET instruction.  The lengths are read from
+// the same word-emitting helpers the epilogue uses rather than assumed: the
+// leaf path shares the prologue's immediate ladder, and a materialised
+// autosize costs its MOV words plus the ADD itself.
 func arm64ReturnEpilogueLen(fi arm64FrameInfo) int {
 	if fi.autosize == 0 {
 		return 0
 	}
 	if fi.leaf {
-		return 8 // ADD + ADD
+		return 4 * (len(arm64AddImmWords(uint32(fi.autosize-8), 29)) +
+			len(arm64AddImmWords(uint32(fi.autosize), 31)))
 	}
 	if fi.autosize <= 0xf0 {
 		return 8 // LDR + LDR.P
 	}
-	return 8 // LDP + ADD
+	// LDP + the deallocation emitted by arm64RetAddWords, so the length
+	// tracks whatever the MOVD ladder needs.
+	return 4 + 4*len(arm64RetAddWords(uint32(fi.autosize)))
 }
 
 // arm64ResolvePseudo translates a pseudo-register memory reference into a
@@ -382,9 +444,12 @@ func arm64GuardBytes(fi arm64FrameInfo, blockStart int) []byte {
 		ws = append(ws, wordsOf(mov)...)
 		ml := len(mov) / 4
 		ws = append(ws, arm64DPExtWords(arm64OpSubs, 27, 31, 17)) // SUBS R17, RSP, R27
-		ws = append(ws, br(8+ml, a64CondLO))
+		// The branches sit at fixed byte offsets in the guard prefix: after
+		// the LDR (4), the ml MOV words (4*ml) and the SUBS (4) for B.LO,
+		// then a further B.LO word and the CMP for B.LS.
+		ws = append(ws, br(8+4*ml, a64CondLO))
 		ws = append(ws, arm64DPSRWords(arm64OpSubs, 16, 17, 31)) // CMP R16, R17
-		ws = append(ws, br(8+ml+8, a64CondLS))
+		ws = append(ws, br(16+4*ml, a64CondLS))
 	}
 	return a64WordsLE(ws...)
 }

asm/assemble.go

@@ -114,6 +114,11 @@ func assemble(t *ast.Text, link *linkInfo) ([]byte, []sbPatch, map[string]int, [
 			if !isJumpMnemonic(mnem) || mnem == "CALL" || long[i] {
 				continue
 			}
+			// A zero-operand jump parses; its arity is reported during
+			// emission (encodeJump), so the layout must not index Operands.
+			if len(s.Operands) != 1 {
+				continue
+			}
 			name, ok := labelName(s.Operands[0])
 			if !ok {
 				continue // reported during emission
@@ -137,28 +142,22 @@ func assemble(t *ast.Text, link *linkInfo) ([]byte, []sbPatch, map[string]int, [
 		}
 		if fi.splitClass == 2 && !guardJBlong {
 			// The underflow JB sits before the CMPQ; its displacement spans
-			// the rest of the guard plus the prologue and the body.
-			jbLen := 2
-			if guardJBlong {
-				jbLen = 6
-			}
-			rest := fi.guardLen(guardJBlong, guardJBElong) - (9 + 3 + 7 + jbLen)
+			// the rest of the guard plus the prologue and the body.  The JB
+			// is still the short form this branch tests (relaxing it is this
+			// branch's job), so guardLen is taken with a short JB and the
+			// subtraction drops the prefix and the JB's own 2 bytes.
+			rest := fi.guardLen(false, guardJBElong) - (9 + 3 + 7 + 2)
 			if !fits8(int64(rest + len(fi.prologue) + bodyLen)) {
 				guardJBlong = true
 				changed = true
 			}
 		}
 		// The morestack JMP returns to the function start, so its
-		// displacement is the negated distance from its own end.
-		if !moreJMPlong {
-			jmpLen := 2
-			if moreJMPlong {
-				jmpLen = 5
-			}
-			if !fits8(-int64(guard + len(fi.prologue) + bodyLen + 5 + jmpLen)) {
-				moreJMPlong = true
-				changed = true
-			}
+		// displacement is the negated distance from its own end; while it is
+		// still short, its own length is 2 bytes.
+		if !moreJMPlong && !fits8(-int64(guard+len(fi.prologue)+bodyLen+5+2)) {
+			moreJMPlong = true
+			changed = true
 		}
 		if !changed {
 			break
@@ -181,7 +180,15 @@ func assemble(t *ast.Text, link *linkInfo) ([]byte, []sbPatch, map[string]int, [
 	var out []byte
 	var patches []sbPatch
 	if fi.needSplit {
-		guard, tlsPatch := buildGuard(fi, int32(len(fi.prologue)+bodyLen), int32(fi.guardLen(guardJBlong, guardJBElong)-(9+3+7+2)+len(fi.prologue)+bodyLen))
+		// The JBE ends the guard, so its displacement is the prologue plus
+		// the body; the underflow JB additionally spans the trailing CMPQ and
+		// JBE, whose combined length is guardLen minus the prefix and the
+		// JB's own length (2 short, 6 long).
+		jbLen := 2
+		if guardJBlong {
+			jbLen = 6
+		}
+		guard, tlsPatch := buildGuard(fi, int32(len(fi.prologue)+bodyLen), int32(fi.guardLen(guardJBlong, guardJBElong)-(9+3+7+jbLen)+len(fi.prologue)+bodyLen))
 		out = append(out, guard...)
 		patches = append(patches, tlsPatch)
 	}
@@ -344,7 +351,10 @@ func computeFrame(t *ast.Text) frameInfo {
 		// pass one extra slot, and the virtual SP is the hardware SP.
 		fi.size = 8
 		fi.useFP = true
-		fi.fpAdjust = int64(fi.size) + 16 // return address + saved BP + args base
+		// The push is the frame: the saved BP sits at SP+0 and the
+		// return address at SP+8, so arguments begin at SP+16.  Unlike
+		// a SUBQ frame, the 8-byte size must not be added again.
+		fi.fpAdjust = 16
 		fi.spAdjust = 0
 		fi.prologue = []byte{0x55, 0x48, 0x89, 0xE5} // PUSHQ BP; MOVQ SP, BP
 		fi.epilogue = []byte{0x5D}                   // POPQ BP
@@ -426,16 +436,6 @@ func (fi frameInfo) guardLen(jbLong, jbeLong bool) int {
 	}
 }
 
-// moreLen returns the byte length of the trailing morestack block: the CALL
-// (always rel32) plus the JMP back to the function start.
-func moreLen(jmpLong bool) int {
-	jmp := 2
-	if jmpLong {
-		jmp = 5
-	}
-	return 5 + jmp
-}
-
 // buildGuard emits the stack-split guard prefix.  jbeDisp and jbDisp are the
 // already-computed displacements of the conditional branches that jump to the
 // morestack block (unused in classes without them).  The TLS load carries a

asm/assemble_test.go

@@ -160,6 +160,57 @@ TEXT ·loadarg(SB), NOSPLIT, $0-24
 	}
 }
 
+// TestAssembleFramelessCall verifies the forced base-pointer frame a $0-frame
+// function containing a CALL receives: the PUSHQ BP prologue with no stack
+// adjustment and the x+N(FP) → (N+16)(SP) translation, against the bytes the
+// Go assembler produces.  The push is the frame, so the offset must not count
+// it twice.
+func TestAssembleFramelessCall(t *testing.T) {
+	f, errs := parser.Parse("frameless_call_amd64.s", `
+#include "textflag.h"
+TEXT ·withcall(SB), NOSPLIT, $0-16
+	MOVQ x+0(FP), AX
+	CALL ·other(SB)
+	MOVQ AX, ret+8(FP)
+	RET
+TEXT ·other(SB), NOSPLIT, $0-0
+	RET
+`)
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFile(f)
+	if err != nil {
+		t.Fatalf("AssembleFile: %v", err)
+	}
+	code := append([]byte(nil), img.Code[img.Funcs[0].Offset:img.Funcs[0].Offset+img.Funcs[0].Size]...)
+	for _, r := range img.Funcs[0].Relocs {
+		for j := r.Off; j < r.Off+4 && j < len(code); j++ {
+			code[j] = 0
+		}
+	}
+	// From `go tool objdump` of the Go-assembled function:
+	//   PUSHQ BP           55
+	//   MOVQ SP, BP        4889e5
+	//   MOVQ 0x10(SP), AX  488b442410
+	//   CALL other         e800000000
+	//   MOVQ AX, 0x18(SP)  4889442418
+	//   POPQ BP            5d
+	//   RET                c3
+	want := []byte{
+		0x55,
+		0x48, 0x89, 0xe5,
+		0x48, 0x8b, 0x44, 0x24, 0x10,
+		0xe8, 0x00, 0x00, 0x00, 0x00,
+		0x48, 0x89, 0x44, 0x24, 0x18,
+		0x5d,
+		0xc3,
+	}
+	if hexBytes(code) != hexBytes(want) {
+		t.Errorf("frameless CALL FP translation mismatch:\n got:  %s\n want: %s", hexBytes(code), hexBytes(want))
+	}
+}
+
 // TestAssembleFrame verifies a function with a non-zero frame: the Go-style
 // prologue/epilogue and the x+N(FP) → (N+frame+16)(SP) translation, against
 // the bytes the Go assembler produces.
@@ -353,6 +404,19 @@ TEXT ·pf(SB), NOSPLIT, $0
 	}
 }
 
+// TestAssembleBareJump checks that a zero-operand jump (which parses, because
+// the parser does not arity-check mnemonics) is rejected with an error rather
+// than panicking in the layout loop, which indexes Operands[0] before the
+// emission pass gets a chance to diagnose the arity.
+func TestAssembleBareJump(t *testing.T) {
+	for _, mnem := range []string{"JE", "JMP", "JLT", "CALL"} {
+		fn := firstText(t, "TEXT ·bare(SB), $16-0\n\t"+mnem+"\n")
+		if _, _, err := Assemble(fn); err == nil {
+			t.Errorf("%s with no operand: expected an error, got none", mnem)
+		}
+	}
+}
+
 // TestSubSPEncodings pins the prologue SUB against the bytes go tool asm
 // emits for SUBQ $size, SP: imm8 for -128..127, the imm32 form for anything
 // larger.  The intermediate 129..255 range used to encode an ADD with a

asm/elf.go

@@ -42,8 +42,10 @@ const (
 	sttSection  = 3
 	stInfoShift = 4
 
-	rX8664PC32    = 2
-	rX8664TPOFF32 = 20
+	rX8664PC32 = 2
+	// R_X86_64_TPOFF32 (debug/elf): the local-exec TLS offset the stack
+	// guard loads from FS.  20 is R_X86_64_TLSLD, a different relocation.
+	rX8664TPOFF32 = 23
 )
 
 // elfSym is one symbol-table entry in construction.
@@ -219,7 +221,7 @@ func (img *Image) ELFObject() ([]byte, error) {
 		for _, r := range relas {
 			var b [24]byte
 			le.PutUint64(b[0:], r.off)
-			le.PutUint64(b[8:], uint64(r.sym)<<32|rX8664PC32)
+			le.PutUint64(b[8:], uint64(r.sym)<<32|uint64(r.typ))
 			le.PutUint64(b[16:], uint64(r.addend))
 			out = append(out, b[:]...)
 		}
@@ -228,15 +230,32 @@ func (img *Image) ELFObject() ([]byte, error) {
 	shstrOff := len(out)
 	out = append(out, stSections.bytes()...)
 
-	// DWARF debug sections (no relocations, the linker resolves DWARF fixups).
+	// DWARF debug sections; the address placeholders they leave are carried
+	// as .rela.debug_info/.rela.debug_line entries the system linker applies.
 	dwAlign := func(n int) {
 		for len(out)%n != 0 {
 			out = append(out, 0)
 		}
 	}
-	dw := appendDWARFSections(&out, img, "gasm.s", symIdx, dwAlign)
+	dw := appendDWARFSections(&out, img, dwarfSourceName(img), symIdx, dwAlign, cfiAMD64)
+	dwarfStart := 0 // section index of .debug_abbrev, set when DWARF is present
 	if dw != nil {
-		nSections += 4 // .debug_abbrev, .debug_info, .debug_line, .debug_line_str
+		// Five DWARF sections: .debug_abbrev, .debug_info, .debug_line,
+		// .debug_line_str and .debug_frame (the CIE is unconditional, so
+		// the frame section is always present), plus the relocation
+		// sections below when they carry entries.
+		dwarfStart = nSections
+		nSections += 5
+		appendDWARFRelas(&out, dw, rX8664Abs64, dwAlign)
+		if dw.infoRelaCount > 0 {
+			nSections++
+		}
+		if dw.lineRelaCount > 0 {
+			nSections++
+		}
+		if dw.frameRelaCount > 0 {
+			nSections++
+		}
 	}
 
 	align(8)
@@ -267,14 +286,37 @@ func (img *Image) ELFObject() ([]byte, error) {
 	}
 	putSh(".shstrtab", shtStrtab, 0, shstrOff, len(stSections.bytes()), 0, 0, 1, 0)
 
-	// DWARF section headers.
+	// DWARF section headers; their indices follow the write order.
 	if dw != nil {
+		// secIdx is a running section index: each putSh below emits the
+		// next header, and the sh_info of a .rela section names the index
+		// of the section it relocates.
+		secIdx := dwarfStart
 		putSh(".debug_abbrev", shtProgbits, 0, dw.abbrevOff, dw.abbrevSize, 0, 0, 1, 0)
+		secIdx++
 		putSh(".debug_info", shtProgbits, 0, dw.infoOff, dw.infoSize, 0, 0, 1, 0)
+		secInfoIdx := secIdx
+		secIdx++
+		if dw.infoRelaCount > 0 {
+			putSh(".rela.debug_info", shtRela, 0, dw.infoRelaOff, 24*dw.infoRelaCount, secSymtab, secInfoIdx, 8, 24)
+			secIdx++
+		}
 		putSh(".debug_line", shtProgbits, 0, dw.lineOff, dw.lineSize, 0, 0, 1, 0)
+		secLineIdx := secIdx
+		secIdx++
+		if dw.lineRelaCount > 0 {
+			putSh(".rela.debug_line", shtRela, 0, dw.lineRelaOff, 24*dw.lineRelaCount, secSymtab, secLineIdx, 8, 24)
+			secIdx++
+		}
 		putSh(".debug_line_str", shtProgbits, 0, dw.lineStrOff, dw.lineStrSize, 0, 0, 1, 0)
+		secIdx++
 		if dw.frameSize > 0 {
 			putSh(".debug_frame", shtProgbits, 0, dw.frameOff, dw.frameSize, 0, 0, 8, 0)
+			secFrameIdx := secIdx
+			secIdx++
+			if dw.frameRelaCount > 0 {
+				putSh(".rela.debug_frame", shtRela, 0, dw.frameRelaOff, 24*dw.frameRelaCount, secSymtab, secFrameIdx, 8, 24)
+			}
 		}
 	}
 

asm/elf_dwarf.go

@@ -12,43 +12,74 @@ import (
 // self-contained sections because the system linker only performs fixup
 // relocations, not assembly.
 
+// DWARF5 attribute, form and line-table constants (the values the
+// toolchain uses, cmd/internal/dwarf/dwarf_defs.go; the DIE streams below
+// are written against these forms).
+const (
+	dwAtName       = 0x03 // DW_AT_name
+	dwAtStmtList   = 0x10 // DW_AT_stmt_list
+	dwAtLowPC      = 0x11 // DW_AT_low_pc
+	dwAtHighPC     = 0x12 // DW_AT_high_pc
+	dwAtDeclFile   = 0x3a // DW_AT_decl_file
+	dwAtDeclLine   = 0x3b // DW_AT_decl_line
+	dwAtExternal   = 0x3f // DW_AT_external
+	dwAtFrameBase  = 0x40 // DW_AT_frame_base
+	dwTagSubprog   = 0x2e // DW_TAG_subprogram
+	dwTagCompUnit  = 0x11 // DW_TAG_compile_unit
+	dwFormAddr     = 0x01 // DW_FORM_addr
+	dwFormData8    = 0x07 // DW_FORM_data8
+	dwFormString   = 0x08 // DW_FORM_string
+	dwFormData1    = 0x0b // DW_FORM_data1
+	dwFormUdata    = 0x0f // DW_FORM_udata
+	dwFormSecOff   = 0x17 // DW_FORM_sec_offset
+	dwFormExprloc  = 0x18 // DW_FORM_exprloc
+	dwFormLineStrp = 0x1f // DW_FORM_line_strp
+	dwLnctPath     = 0x01 // DW_LNCT_path
+	dwLnctDirIndex = 0x02 // DW_LNCT_directory_index
+)
+
 // dwarfAbbrevTable returns the .debug_abbrev content: a single compilation
-// unit with DW_TAG_compile_unit and DW_TAG_subprogram entries.
+// unit with DW_TAG_compile_unit and DW_TAG_subprogram entries.  The
+// attribute/form pairs must match the DIE streams dwarfBuildInfoSection
+// writes byte for byte, in the same order, or every consumer's parse of
+// .debug_info desynchronises.
 func dwarfAbbrevTable() []byte {
 	var b []byte
-	// Abbrev 1: DW_TAG_compile_unit
-	b = append(b, 1)        // abbreviation code
-	b = append(b, 0x11)     // DW_TAG_compile_unit
-	b = append(b, 1)        // DW_CHILDREN_yes
-	b = appendUleb(b, 0x1b) // DW_AT_low_pc
-	b = appendUleb(b, 0x01) // DW_FORM_addr
-	b = appendUleb(b, 0x29) // DW_AT_high_pc
-	b = appendUleb(b, 0x07) // DW_FORM_data8
-	b = appendUleb(b, 0x10) // DW_AT_stmt_list
-	b = appendUleb(b, 0x25) // DW_FORM_sec_offset
-	b = appendUleb(b, 0x01) // DW_AT_name
-	b = appendUleb(b, 0x08) // DW_FORM_string
-	b = appendUleb(b, 0)    // end of attributes
+	// Abbrev 1: DW_TAG_compile_unit.
+	b = append(b, 1)                 // abbreviation code
+	b = appendUleb(b, dwTagCompUnit) // DW_TAG_compile_unit
+	b = append(b, 1)                 // DW_CHILDREN_yes
+	b = appendUleb(b, dwAtLowPC)     // DW_AT_low_pc
+	b = appendUleb(b, dwFormAddr)    // DW_FORM_addr
+	b = appendUleb(b, dwAtHighPC)    // DW_AT_high_pc
+	b = appendUleb(b, dwFormData8)   // DW_FORM_data8
+	b = appendUleb(b, dwAtStmtList)  // DW_AT_stmt_list
+	b = appendUleb(b, dwFormSecOff)  // DW_FORM_sec_offset (4 bytes here)
+	b = appendUleb(b, dwAtName)      // DW_AT_name
+	b = appendUleb(b, dwFormString)  // DW_FORM_string
+	b = appendUleb(b, 0)             // end of attributes: attr 0
+	b = appendUleb(b, 0)             // ... paired with form 0
 
-	// Abbrev 2: DW_TAG_subprogram
-	b = append(b, 2)        // abbreviation code
-	b = append(b, 0x2e)     // DW_TAG_subprogram
-	b = append(b, 0)        // DW_CHILDREN_no
-	b = appendUleb(b, 0x03) // DW_AT_name
-	b = appendUleb(b, 0x08) // DW_FORM_string
-	b = appendUleb(b, 0x11) // DW_AT_low_pc
-	b = appendUleb(b, 0x01) // DW_FORM_addr
-	b = appendUleb(b, 0x29) // DW_AT_high_pc
-	b = appendUleb(b, 0x07) // DW_FORM_data8
-	b = appendUleb(b, 0x3f) // DW_AT_frame_base
-	b = appendUleb(b, 0x18) // DW_FORM_exprloc
-	b = appendUleb(b, 0x3b) // DW_AT_decl_file
-	b = appendUleb(b, 0x0b) // DW_FORM_data1
-	b = appendUleb(b, 0x37) // DW_AT_decl_line
-	b = appendUleb(b, 0x0b) // DW_FORM_data1
-	b = appendUleb(b, 0x63) // DW_AT_external
-	b = appendUleb(b, 0x0b) // DW_FORM_flag
-	b = appendUleb(b, 0)    // end of attributes
+	// Abbrev 2: DW_TAG_subprogram.
+	b = append(b, 2)                 // abbreviation code
+	b = appendUleb(b, dwTagSubprog)  // DW_TAG_subprogram
+	b = append(b, 0)                 // DW_CHILDREN_no
+	b = appendUleb(b, dwAtName)      // DW_AT_name
+	b = appendUleb(b, dwFormString)  // DW_FORM_string
+	b = appendUleb(b, dwAtLowPC)     // DW_AT_low_pc
+	b = appendUleb(b, dwFormAddr)    // DW_FORM_addr
+	b = appendUleb(b, dwAtHighPC)    // DW_AT_high_pc
+	b = appendUleb(b, dwFormData8)   // DW_FORM_data8
+	b = appendUleb(b, dwAtFrameBase) // DW_AT_frame_base
+	b = appendUleb(b, dwFormExprloc) // DW_FORM_exprloc
+	b = appendUleb(b, dwAtDeclFile)  // DW_AT_decl_file
+	b = appendUleb(b, dwFormData1)   // DW_FORM_data1
+	b = appendUleb(b, dwAtDeclLine)  // DW_AT_decl_line
+	b = appendUleb(b, dwFormData1)   // DW_FORM_data1
+	b = appendUleb(b, dwAtExternal)  // DW_AT_external
+	b = appendUleb(b, 0x0c)          // DW_FORM_flag (one byte, 0 or 1)
+	b = appendUleb(b, 0)             // end of attributes: attr 0
+	b = appendUleb(b, 0)             // ... paired with form 0
 
 	// End of table.
 	b = append(b, 0)
@@ -68,6 +99,9 @@ type dwarfSections struct {
 	infoRelocs []dwarfReloc
 	// Relocations for .debug_line: (offset, symbol name, addend).
 	lineRelocs []dwarfReloc
+	// Relocations for .debug_frame: (offset, symbol name, addend), one per
+	// FDE initial_location.
+	frameRelocs []dwarfReloc
 }
 
 type dwarfReloc struct {
@@ -76,8 +110,9 @@ type dwarfReloc struct {
 	addend int64
 }
 
-// emitDWARF generates complete DWARF5 sections for the image.
-func emitDWARF(img *Image, srcFile string) *dwarfSections {
+// emitDWARF generates complete DWARF5 sections for the image.  cfi carries
+// the architecture's .debug_frame register conventions.
+func emitDWARF(img *Image, srcFile string, cfi cfiArch) *dwarfSections {
 	ds := &dwarfSections{}
 	ds.debugAbbrev = dwarfAbbrevTable()
 
@@ -86,19 +121,21 @@ func emitDWARF(img *Image, srcFile string) *dwarfSections {
 	lineStr.add(srcFile)
 	ds.debugLineStr = lineStr.bytes()
 
-	// Build .debug_line.
-	ds.debugLine = dwarfBuildLineSection(img, ds)
+	// Build .debug_line; the file table references the source name through
+	// its offset in .debug_line_str.
+	ds.debugLine = dwarfBuildLineSection(img, uint32(lineStr.at(srcFile)), ds)
 
 	// Build .debug_info.
 	ds.debugInfo = dwarfBuildInfoSection(img, srcFile, ds)
 
 	// Build .debug_frame.
-	ds.debugFrame = dwarfBuildFrameSection(img)
+	ds.debugFrame = dwarfBuildFrameSection(img, cfi, ds)
 	return ds
 }
 
-// dwarfBuildLineSection builds a complete .debug_line section.
-func dwarfBuildLineSection(img *Image, ds *dwarfSections) []byte {
+// dwarfBuildLineSection builds a complete .debug_line section.  srcStrOff is
+// the source file name's offset in .debug_line_str.
+func dwarfBuildLineSection(img *Image, srcStrOff uint32, ds *dwarfSections) []byte {
 	var b []byte
 	le := binary.LittleEndian
 
@@ -120,15 +157,25 @@ func dwarfBuildLineSection(img *Image, ds *dwarfSections) []byte {
 	// Standard opcode lengths (opcode 1..opcode_base-1).
 	b = append(b, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0)
 
-	// Directory table (DWARF5 format).
-	b = append(b, 0) // one directory entry (index 0 = empty)
-	// File table.
-	b = appendUleb(b, 1) // file count
-	// File 1: name index into .debug_line_str, dir index, time, size.
-	b = appendUleb(b, 0) // name (index 0 in line_str)
-	b = appendUleb(b, 0) // directory index
-	b = appendUleb(b, 0) // last modification time
-	b = appendUleb(b, 0) // file size
+	// Directory table (DWARF5 §6.2.4): entry format descriptors followed by
+	// the entries.  One directory, the compilation directory, whose path is
+	// the empty string at .debug_line_str offset 0.
+	b = append(b, 1)                  // directory_entry_format_count
+	b = appendUleb(b, dwLnctPath)     // DW_LNCT_path
+	b = appendUleb(b, dwFormLineStrp) // DW_FORM_line_strp
+	b = appendUleb(b, 1)              // directories_count
+	b = le.AppendUint32(b, 0)         // .debug_line_str offset of ""
+
+	// File table (DWARF5 §6.2.5).  v5 indexes files from 0, so the source
+	// file is entry 0, matching the DW_AT_decl_file value 0 the DIEs carry.
+	b = append(b, 2)                  // file_name_entry_format_count
+	b = appendUleb(b, dwLnctPath)     // DW_LNCT_path
+	b = appendUleb(b, dwFormLineStrp) // DW_FORM_line_strp
+	b = appendUleb(b, dwLnctDirIndex) // DW_LNCT_directory_index
+	b = appendUleb(b, dwFormUdata)    // DW_FORM_udata
+	b = appendUleb(b, 1)              // file_names_count
+	b = le.AppendUint32(b, srcStrOff) // .debug_line_str offset of the source name
+	b = appendUleb(b, 0)              // directory index 0 (the compilation directory)
 
 	headerEnd := len(b)
 
@@ -176,8 +223,11 @@ func dwarfBuildLineSection(img *Image, ds *dwarfSections) []byte {
 
 	// Patch unit_length.
 	le.PutUint32(b[headerStart:], uint32(len(b)-headerStart-4))
-	// Patch header_length.
-	le.PutUint32(b[headerStart+6:], uint32(headerEnd-headerStart-10))
+	// Patch header_length.  In the v5 header it follows the one-byte
+	// address_size and segment_selector_size (offset 8, not the DWARF2-4
+	// offset 6), and counts from just past itself to the first program
+	// byte.
+	le.PutUint32(b[headerStart+8:], uint32(headerEnd-headerStart-12))
 	return b
 }
 
@@ -195,14 +245,16 @@ func dwarfBuildInfoSection(img *Image, srcFile string, ds *dwarfSections) []byte
 
 	// DW_TAG_compile_unit (abbrev 1).
 	b = append(b, 1) // abbreviation code
-	// DW_AT_low_pc: address of .text start.
-	infoRelocBase := len(b)
+	// DW_AT_low_pc: address of .text start.  A data-only image has no
+	// functions to relocate against; its CU covers no code, so the base
+	// stays zero (the DWARF "no base address" value) with no relocation.
 	b = le.AppendUint64(b, 0) // placeholder
-	ds.infoRelocs = append(ds.infoRelocs, dwarfReloc{
-		off:    uint64(infoRelocBase),
-		name:   img.Funcs[0].Name,
-		addend: 0,
-	})
+	if len(img.Funcs) > 0 {
+		ds.infoRelocs = append(ds.infoRelocs, dwarfReloc{
+			off:  uint64(len(b) - 8),
+			name: img.Funcs[0].Name,
+		})
+	}
 	// DW_AT_high_pc: size of .text.
 	b = le.AppendUint64(b, uint64(len(img.Code)))
 	// DW_AT_stmt_list: offset into .debug_line (0).
@@ -229,8 +281,9 @@ func dwarfBuildInfoSection(img *Image, srcFile string, ds *dwarfSections) []byte
 		b = le.AppendUint64(b, uint64(fn.Size))
 		// DW_AT_frame_base: DW_OP_call_frame_cfa.
 		b = append(b, 1, 0x9c)
-		// DW_AT_decl_file: file index 1.
-		b = append(b, 1)
+		// DW_AT_decl_file: the single file-table entry, index 0 (v5 indexes
+		// files from 0).
+		b = append(b, 0)
 		// DW_AT_decl_line.
 		b = append(b, uint8(fn.Line))
 		// DW_AT_external.
@@ -253,32 +306,61 @@ func appendUleb(b []byte, v uint64) []byte {
 	return binary.AppendUvarint(b, v)
 }
 
+// appendSleb appends v in signed LEB128, the encoding DWARF specifies:
+// two's-complement sign extension, which is NOT Go's zigzag varint
+// (binary.AppendVarint(-8) encodes 15, where DWARF wants 0x78).
 func appendSleb(b []byte, v int64) []byte {
-	return binary.AppendVarint(b, v)
+	for {
+		c := byte(v & 0x7f)
+		v >>= 7
+		if (v == 0 && c&0x40 == 0) || (v == -1 && c&0x40 != 0) {
+			return append(b, c)
+		}
+		b = append(b, c|0x80)
+	}
 }
 
+// cfiArch carries the .debug_frame CIE parameters that differ per
+// architecture: the DWARF register numbers of the stack pointer the initial
+// CFA rule names and of the return address.  The values are the ones the Go
+// linker writes into its own CIE (cmd/link/internal/ld/dwarf.go uses
+// Dwarfregsp and Dwarfreglr; the per-architecture constants live in
+// cmd/link/internal/<arch>/l.go).
+type cfiArch struct {
+	name   string
+	cfaReg byte // the stack-pointer register the initial CFA rule names
+	raReg  byte // the return-address register
+}
+
+var (
+	cfiAMD64   = cfiArch{"amd64", 7, 16}  // RSP, RIP
+	cfiARM64   = cfiArch{"arm64", 31, 30} // SP (X31), LR (X30)
+	cfiRISCV64 = cfiArch{"riscv64", 2, 1} // X2 (sp), X1 (ra)
+	cfiLOONG64 = cfiArch{"loong64", 3, 1} // $r3 (sp), $r1 (ra)
+)
+
 // dwarfBuildFrameSection builds a .debug_frame section with CFI for stack
 // unwinding.  It emits one CIE and one FDE per function, encoding the
 // CFA (Canonical Frame Address) rule changes at each stack-adjustment
 // boundary recorded in FuncLayout.Spadj.
-func dwarfBuildFrameSection(img *Image) []byte {
+func dwarfBuildFrameSection(img *Image, cfi cfiArch, ds *dwarfSections) []byte {
 	var b []byte
 	le := binary.LittleEndian
 
 	// CIE (Common Information Entry).
 	cieStart := len(b)
-	b = append(b, 0, 0, 0, 0)          // length (placeholder)
-	b = le.AppendUint32(b, 0xFFFFFFFF) // CIE marker
-	b = append(b, 3)                   // version (DWARF3, widely supported)
-	b = append(b, 0)                   // augmentation (empty)
-	b = appendUleb(b, 1)               // code alignment
-	b = appendSleb(b, -8)              // data alignment (-8 for 64-bit)
-	b = appendUleb(b, 16)              // return address register (LR on arm64, RIP on amd64)
+	b = append(b, 0, 0, 0, 0)            // length (placeholder)
+	b = le.AppendUint32(b, 0xFFFFFFFF)   // CIE marker
+	b = append(b, 3)                     // version (DWARF3, widely supported)
+	b = append(b, 0)                     // augmentation (empty)
+	b = appendUleb(b, 1)                 // code alignment
+	b = appendSleb(b, -8)                // data alignment (-8 for 64-bit)
+	b = appendUleb(b, uint64(cfi.raReg)) // return address register
 	// Initial CFA rule: DW_CFA_def_cfa (SP, 0)
-	b = append(b, 0x0c)   // DW_CFA_def_cfa
-	b = appendUleb(b, 31) // register: SP (RSP=7 on amd64, SP=31 on arm64)
-	b = appendUleb(b, 0)  // offset: 0
-	b = append(b, 0)      // DW_CFA_nop (padding)
+	b = append(b, 0x0c)                   // DW_CFA_def_cfa
+	b = appendUleb(b, uint64(cfi.cfaReg)) // the architecture's stack pointer
+	b = appendUleb(b, 0)                  // offset: 0
+	b = append(b, 0)                      // DW_CFA_nop (padding)
 	// Patch CIE length.
 	le.PutUint32(b[cieStart:], uint32(len(b)-cieStart-4))
 
@@ -287,7 +369,12 @@ func dwarfBuildFrameSection(img *Image) []byte {
 		fdeStart := len(b)
 		b = append(b, 0, 0, 0, 0)                // length (placeholder)
 		b = le.AppendUint32(b, uint32(cieStart)) // CIE pointer (offset from start)
-		// Initial location: function offset in .text (relocated by linker).
+		// Initial location: function offset in .text, referenced through
+		// the function's symbol so the linker relocates it.
+		ds.frameRelocs = append(ds.frameRelocs, dwarfReloc{
+			off:  uint64(fdeStart + 8),
+			name: fn.Name,
+		})
 		b = le.AppendUint64(b, uint64(fn.Offset))
 		// Address range: function size.
 		b = le.AppendUint64(b, uint64(fn.Size))

asm/elf_dwarf_sections.go

@@ -3,6 +3,17 @@
 
 package asm
 
+import "encoding/binary"
+
+// Absolute 64-bit relocation types for the DWARF address fixups, one per
+// supported architecture (the numbers debug/elf carries).
+const (
+	rX8664Abs64   = 1   // R_X86_64_64
+	rAARCH64Abs64 = 257 // R_AARCH64_ABS64
+	rRISCVAbs64   = 2   // R_RISCV_64
+	rLarchAbs64   = 2   // R_LARCH_64
+)
+
 // dwarfELFSections holds the laid-out DWARF sections ready for inclusion
 // in an ELF file.
 type dwarfELFSections struct {
@@ -11,15 +22,23 @@ type dwarfELFSections struct {
 	lineOff, lineSize       int
 	lineStrOff, lineStrSize int
 	frameOff, frameSize     int
-	// Relocations for .debug_info address references.
+	// .rela.debug_info and .rela.debug_line contents: file offsets and
+	// entry counts (zero count: the section is absent).
+	infoRelaOff, infoRelaCount   int
+	lineRelaOff, lineRelaCount   int
+	frameRelaOff, frameRelaCount int
+	// Relocations for .debug_info address references, offsets relative to
+	// the section start (what an r_offset in .rela.debug_info means).
 	infoRelocs []elfDwarfReloc
-	// Relocations for .debug_line address references.
+	// Relocations for .debug_line address references, section-relative.
 	lineRelocs []elfDwarfReloc
+	// Relocations for .debug_frame FDE initial locations, section-relative.
+	frameRelocs []elfDwarfReloc
 }
 
 type elfDwarfReloc struct {
-	off    uint64
-	sym    int // symbol index in .symtab
+	off    uint64 // offset within the target section
+	sym    int    // symbol index in .symtab
 	addend int64
 }
 
@@ -29,8 +48,9 @@ type elfDwarfReloc struct {
 //
 // symIdx maps function names to their .symtab indices (needed for relocations
 // against .text symbols).  The map uses objectName format (pkg.name); the
-// DWARF code uses bare function names, so we build a reverse lookup.
-func appendDWARFSections(out *[]byte, img *Image, srcFile string, symIdx map[string]int, align func(int)) *dwarfELFSections {
+// DWARF code uses bare function names, so we build a reverse lookup.  cfi
+// carries the architecture's .debug_frame register conventions.
+func appendDWARFSections(out *[]byte, img *Image, srcFile string, symIdx map[string]int, align func(int), cfi cfiArch) *dwarfELFSections {
 	// Build a lookup from bare function name to symbol index.
 	nameToIdx := make(map[string]int, len(symIdx))
 	for name, idx := range symIdx {
@@ -45,7 +65,7 @@ func appendDWARFSections(out *[]byte, img *Image, srcFile string, symIdx map[str
 		}
 		nameToIdx[name] = idx
 	}
-	ds := emitDWARF(img, srcFile)
+	ds := emitDWARF(img, srcFile, cfi)
 	if ds == nil || len(ds.debugAbbrev) == 0 {
 		return nil
 	}
@@ -68,15 +88,11 @@ func appendDWARFSections(out *[]byte, img *Image, srcFile string, symIdx map[str
 	align(1)
 	result.lineOff = len(*out)
 	result.lineSize = len(ds.debugLine)
-	lineBase := len(*out)
 	*out = append(*out, ds.debugLine...)
-
-	// Patch .debug_line relocations: replace placeholder addresses with
-	// actual .text offsets via symbol lookup.
 	for _, dr := range ds.lineRelocs {
 		if idx, ok := nameToIdx[dr.name]; ok {
 			result.lineRelocs = append(result.lineRelocs, elfDwarfReloc{
-				off:    uint64(lineBase) + dr.off,
+				off:    dr.off,
 				sym:    idx,
 				addend: dr.addend,
 			})
@@ -87,33 +103,77 @@ func appendDWARFSections(out *[]byte, img *Image, srcFile string, symIdx map[str
 	align(1)
 	result.infoOff = len(*out)
 	result.infoSize = len(ds.debugInfo)
-	infoBase := len(*out)
 	*out = append(*out, ds.debugInfo...)
-
-	// .debug_frame
-	if len(ds.debugFrame) > 0 {
-		align(1)
-		result.frameOff = len(*out)
-		result.frameSize = len(ds.debugFrame)
-		*out = append(*out, ds.debugFrame...)
-	}
-
-	// Patch .debug_info relocations.
 	for _, dr := range ds.infoRelocs {
 		if idx, ok := nameToIdx[dr.name]; ok {
 			result.infoRelocs = append(result.infoRelocs, elfDwarfReloc{
-				off:    uint64(infoBase) + dr.off,
+				off:    dr.off,
 				sym:    idx,
 				addend: dr.addend,
 			})
 		}
 	}
 
+	// .debug_frame: the section header declares alignment 8, so the data is
+	// padded to 8, matching it.
+	if len(ds.debugFrame) > 0 {
+		align(8)
+		result.frameOff = len(*out)
+		result.frameSize = len(ds.debugFrame)
+		*out = append(*out, ds.debugFrame...)
+		for _, dr := range ds.frameRelocs {
+			if idx, ok := nameToIdx[dr.name]; ok {
+				result.frameRelocs = append(result.frameRelocs, elfDwarfReloc{
+					off:    dr.off,
+					sym:    idx,
+					addend: dr.addend,
+				})
+			}
+		}
+	}
+
 	return result
 }
 
+// appendDWARFRelas writes the .rela.debug_info and .rela.debug_line section
+// bodies from the relocations appendDWARFSections recorded, with the
+// architecture's absolute 64-bit relocation type, and records their file
+// offsets and entry counts on dw.  Called after the DWARF sections
+// themselves so the r_offsets (section-relative) need no adjustment.
+func appendDWARFRelas(out *[]byte, dw *dwarfELFSections, abs64 uint32, align func(int)) {
+	le := binary.LittleEndian
+	write := func(relas []elfDwarfReloc) (off, count int) {
+		if len(relas) == 0 {
+			return 0, 0
+		}
+		align(8)
+		off = len(*out)
+		for _, r := range relas {
+			var b [24]byte
+			le.PutUint64(b[0:], r.off)
+			le.PutUint64(b[8:], uint64(r.sym)<<32|uint64(abs64))
+			le.PutUint64(b[16:], uint64(r.addend))
+			*out = append(*out, b[:]...)
+		}
+		return off, len(relas)
+	}
+	dw.infoRelaOff, dw.infoRelaCount = write(dw.infoRelocs)
+	dw.lineRelaOff, dw.lineRelaCount = write(dw.lineRelocs)
+	dw.frameRelaOff, dw.frameRelaCount = write(dw.frameRelocs)
+}
+
+// dwarfSourceName returns the source name the DWARF sections record: the
+// image's source path when the assembler captured one, "gasm.s" otherwise.
+func dwarfSourceName(img *Image) string {
+	if img.SourcePath != "" {
+		return img.SourcePath
+	}
+	return "gasm.s"
+}
+
 // dwarfSectionNames returns the DWARF section names for the string table.
 var dwarfSectionNames = []string{
 	".debug_abbrev", ".debug_info", ".debug_line", ".debug_line_str",
 	".debug_frame", ".rela.debug_info", ".rela.debug_line",
+	".rela.debug_frame",
 }

asm/elf_dwarf_test.go

@@ -4,11 +4,313 @@
 package asm
 
 import (
+	"bytes"
+	"encoding/binary"
 	"testing"
 
 	"sourcedock.dev/petrbalvin/gasm-devkit/parser"
 )
 
+// ulebIter reads ULEB128 values, the .debug_abbrev and line-header
+// encoding.
+type ulebIter struct {
+	b []byte
+	i int
+}
+
+func (r *ulebIter) uleb(t *testing.T) uint64 {
+	t.Helper()
+	v, n := binary.Uvarint(r.b[r.i:])
+	if n <= 0 {
+		t.Fatalf("bad ULEB at %d", r.i)
+	}
+	r.i += n
+	return v
+}
+
+func (r *ulebIter) byteAt(t *testing.T) byte {
+	t.Helper()
+	if r.i >= len(r.b) {
+		t.Fatalf("read past end at %d", r.i)
+	}
+	c := r.b[r.i]
+	r.i++
+	return c
+}
+
+func (r *ulebIter) uint32At(t *testing.T) uint32 {
+	t.Helper()
+	v := binary.LittleEndian.Uint32(r.b[r.i:])
+	r.i += 4
+	return v
+}
+
+// sleb reads a signed LEB128, the DWARF encoding (sign-extended two's
+// complement, not Go's zigzag varint).
+func (r *ulebIter) sleb(t *testing.T) int64 {
+	t.Helper()
+	var v int64
+	var shift uint
+	for {
+		c := r.byteAt(t)
+		v |= int64(c&0x7f) << shift
+		shift += 7
+		if c&0x80 == 0 {
+			if c&0x40 != 0 {
+				v |= -1 << shift
+			}
+			return v
+		}
+	}
+}
+
+// dwarfAttr is one attribute/form pair of an abbreviation.
+type dwarfAttr struct{ attr, form uint64 }
+
+// dwarfAbbrev is one parsed abbreviation declaration.
+type dwarfAbbrev struct {
+	code     uint64
+	tag      uint64
+	children bool
+	attrs    []dwarfAttr
+}
+
+// parseAbbrevs walks a .debug_abbrev table: abbreviation code, tag,
+// children flag, then attr/form ULEB pairs terminated by a double zero.
+func parseAbbrevs(t *testing.T, b []byte) map[uint64]dwarfAbbrev {
+	t.Helper()
+	out := map[uint64]dwarfAbbrev{}
+	r := &ulebIter{b: b}
+	for {
+		code := r.uleb(t)
+		if code == 0 {
+			return out
+		}
+		ab := dwarfAbbrev{code: code, tag: r.uleb(t)}
+		ab.children = r.byteAt(t) == 1
+		for {
+			attr := r.uleb(t)
+			form := r.uleb(t)
+			if attr == 0 && form == 0 {
+				break
+			}
+			if attr == 0 || form == 0 {
+				t.Fatalf("abbrev %d: half-terminated attr/form pair (%d, %d)", code, attr, form)
+			}
+			ab.attrs = append(ab.attrs, dwarfAttr{attr, form})
+		}
+		out[code] = ab
+	}
+}
+
+func eqAttrs(t *testing.T, ab dwarfAbbrev, want []dwarfAttr) {
+	t.Helper()
+	if len(ab.attrs) != len(want) {
+		t.Fatalf("abbrev %d attrs = %v, want %v", ab.code, ab.attrs, want)
+	}
+	for i, w := range want {
+		if ab.attrs[i] != w {
+			t.Fatalf("abbrev %d attr %d = (%#x, %#x), want (%#x, %#x)", ab.code, i, ab.attrs[i].attr, ab.attrs[i].form, w.attr, w.form)
+		}
+	}
+}
+
+// TestDwarfAbbrevTable walks the abbreviation table as a consumer does and
+// checks the attribute/form sets against the constants the toolchain uses
+// (cmd/internal/dwarf/dwarf_defs.go).  A wrong constant here renames an
+// attribute (0x1b is comp_dir, not low_pc; 0x29 and 0x37 are bounds and
+// count) and a wrong form desynchronises the DIE parse: 0x25 is strx1, one
+// byte, where the writer emits four for a section offset.
+func TestDwarfAbbrevTable(t *testing.T) {
+	abbrev := dwarfAbbrevTable()
+	if len(abbrev) == 0 {
+		t.Fatal("empty abbrev table")
+	}
+	// Must end with a zero byte (end of table).
+	if abbrev[len(abbrev)-1] != 0 {
+		t.Fatalf("abbrev table last byte = %d, want 0", abbrev[len(abbrev)-1])
+	}
+	abs := parseAbbrevs(t, abbrev)
+	if len(abs) != 2 {
+		t.Fatalf("abbreviations = %d, want 2", len(abs))
+	}
+	cu, ok := abs[1]
+	if !ok {
+		t.Fatal("missing abbreviation 1 (compile unit)")
+	}
+	if cu.tag != dwTagCompUnit || !cu.children {
+		t.Errorf("abbrev 1: tag %#x children %v, want compile unit with children", cu.tag, cu.children)
+	}
+	eqAttrs(t, cu, []dwarfAttr{
+		{dwAtLowPC, dwFormAddr},
+		{dwAtHighPC, dwFormData8},
+		{dwAtStmtList, dwFormSecOff},
+		{dwAtName, dwFormString},
+	})
+	sp, ok := abs[2]
+	if !ok {
+		t.Fatal("missing abbreviation 2 (subprogram)")
+	}
+	if sp.tag != dwTagSubprog || sp.children {
+		t.Errorf("abbrev 2: tag %#x children %v, want subprogram without children", sp.tag, sp.children)
+	}
+	eqAttrs(t, sp, []dwarfAttr{
+		{dwAtName, dwFormString},
+		{dwAtLowPC, dwFormAddr},
+		{dwAtHighPC, dwFormData8},
+		{dwAtFrameBase, dwFormExprloc},
+		{dwAtDeclFile, dwFormData1},
+		{dwAtDeclLine, dwFormData1},
+		{dwAtExternal, 0x0c}, // DW_FORM_flag
+	})
+}
+
+// TestDwarfLineHeaderV5 parses the .debug_line header under DWARF5 rules:
+// the directory and file tables are format-descriptor lists, not the
+// DWARF2-4 shape of null-terminated strings, and the file entry references
+// the source name through .debug_line_str.
+func TestDwarfLineHeaderV5(t *testing.T) {
+	src := `#include "textflag.h"
+TEXT ·add(SB), NOSPLIT, $0-24
+	MOVQ a+0(FP), AX
+	MOVQ b+8(FP), BX
+	ADDQ BX, AX
+	MOVQ AX, ret+16(FP)
+	RET
+`
+	f, errs := parser.Parse("test_amd64.s", src)
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFile(f)
+	if err != nil {
+		t.Fatalf("assemble: %v", err)
+	}
+
+	ds := emitDWARF(img, "test_amd64.s", cfiAMD64)
+	r := &ulebIter{b: ds.debugLine}
+	r.uint32At(t) // unit_length
+	if v := binary.LittleEndian.Uint16(ds.debugLine[4:]); v != 5 {
+		t.Fatalf("version = %d, want 5", v)
+	}
+	r.i = 6
+	r.byteAt(t)   // address_size
+	r.byteAt(t)   // segment_selector_size
+	r.uint32At(t) // header_length
+	r.byteAt(t)   // minimum_instruction_length
+	r.byteAt(t)   // maximum_ops_per_instruction
+	r.byteAt(t)   // default_is_stmt
+	r.byteAt(t)   // line_base
+	r.byteAt(t)   // line_range
+	opcodeBase := r.byteAt(t)
+	for range int(opcodeBase) - 1 {
+		r.byteAt(t) // standard opcode lengths
+	}
+
+	// Directory table (DWARF5 §6.2.4).
+	if n := r.byteAt(t); n != 1 {
+		t.Fatalf("directory_entry_format_count = %d, want 1", n)
+	}
+	if lnct := r.uleb(t); lnct != dwLnctPath {
+		t.Errorf("directory content type = %#x, want DW_LNCT_path", lnct)
+	}
+	if form := r.uleb(t); form != dwFormLineStrp {
+		t.Errorf("directory form = %#x, want DW_FORM_line_strp", form)
+	}
+	if n := r.uleb(t); n != 1 {
+		t.Fatalf("directories_count = %d, want 1", n)
+	}
+	if off := r.uint32At(t); off != 0 {
+		t.Errorf("compilation directory line_strp = %d, want 0 (the empty string)", off)
+	}
+
+	// File table (DWARF5 §6.2.5).
+	if n := r.byteAt(t); n != 2 {
+		t.Fatalf("file_name_entry_format_count = %d, want 2", n)
+	}
+	if lnct := r.uleb(t); lnct != dwLnctPath {
+		t.Errorf("file content type = %#x, want DW_LNCT_path", lnct)
+	}
+	if form := r.uleb(t); form != dwFormLineStrp {
+		t.Errorf("file path form = %#x, want DW_FORM_line_strp", form)
+	}
+	if lnct := r.uleb(t); lnct != dwLnctDirIndex {
+		t.Errorf("file content type = %#x, want DW_LNCT_directory_index", lnct)
+	}
+	if form := r.uleb(t); form != dwFormUdata {
+		t.Errorf("file dir-index form = %#x, want DW_FORM_udata", form)
+	}
+	if n := r.uleb(t); n != 1 {
+		t.Fatalf("file_names_count = %d, want 1", n)
+	}
+	strOff := r.uint32At(t)
+	if dirIdx := r.uleb(t); dirIdx != 0 {
+		t.Errorf("file directory index = %d, want 0", dirIdx)
+	}
+
+	// The file entry's line_strp must resolve to the source name.
+	end := int(strOff) + len("test_amd64.s")
+	if int(strOff) >= len(ds.debugLineStr) || !bytes.Equal(ds.debugLineStr[strOff:end], []byte("test_amd64.s")) {
+		t.Errorf("file entry line_strp %d does not name the source: %q", strOff, ds.debugLineStr)
+	}
+
+	// The fixed header fields: address_size 8 and a header_length that
+	// points just past the file table (the patch site is offset 8 in the
+	// v5 header, and the field counts from its own end).
+	if ds.debugLine[6] != 8 || ds.debugLine[7] != 0 {
+		t.Errorf("address_size/segment_selector = %d/%d, want 8/0", ds.debugLine[6], ds.debugLine[7])
+	}
+	if hl := binary.LittleEndian.Uint32(ds.debugLine[8:]); hl != uint32(r.i-12) {
+		t.Errorf("header_length = %d, want %d (the byte after the file table is %d)", hl, r.i-12, r.i)
+	}
+}
+
+// TestDwarfFrameCIEArch checks the shared CIE carries each architecture's
+// stack-pointer and return-address registers: the values the Go linker
+// writes (cmd/link/internal/<arch>/l.go dwarfRegSP/dwarfRegLR).
+func TestDwarfFrameCIEArch(t *testing.T) {
+	for _, tc := range []struct {
+		name string
+		cfi  cfiArch
+	}{
+		{"amd64", cfiAMD64},
+		{"arm64", cfiARM64},
+		{"riscv64", cfiRISCV64},
+		{"loong64", cfiLOONG64},
+	} {
+		frame := dwarfBuildFrameSection(&Image{}, tc.cfi, &dwarfSections{})
+		r := &ulebIter{b: frame}
+		r.uint32At(t) // length
+		if cid := r.uint32At(t); cid != 0xFFFFFFFF {
+			t.Errorf("%s: CIE id = %#x, want 0xffffffff", tc.name, cid)
+		}
+		if v := r.byteAt(t); v != 3 {
+			t.Errorf("%s: CIE version = %d, want 3", tc.name, v)
+		}
+		if aug := r.byteAt(t); aug != 0 {
+			t.Errorf("%s: CIE augmentation = %d, want 0", tc.name, aug)
+		}
+		if ca := r.uleb(t); ca != 1 {
+			t.Errorf("%s: code alignment = %d, want 1", tc.name, ca)
+		}
+		if da := r.sleb(t); da != -8 {
+			t.Errorf("%s: data alignment = %d, want -8 (signed LEB128, not zigzag)", tc.name, da)
+		}
+		if ra := r.uleb(t); ra != uint64(tc.cfi.raReg) {
+			t.Errorf("%s: return-address register = %d, want %d", tc.name, ra, tc.cfi.raReg)
+		}
+		if op := r.byteAt(t); op != 0x0c {
+			t.Errorf("%s: expected DW_CFA_def_cfa, got opcode %#x", tc.name, op)
+		}
+		if cfa := r.uleb(t); cfa != uint64(tc.cfi.cfaReg) {
+			t.Errorf("%s: CFA register = %d, want %d", tc.name, cfa, tc.cfi.cfaReg)
+		}
+		if off := r.uleb(t); off != 0 {
+			t.Errorf("%s: CFA offset = %d, want 0", tc.name, off)
+		}
+	}
+}
+
 func TestEmitDWARF(t *testing.T) {
 	src := `#include "textflag.h"
 TEXT ·add(SB), NOSPLIT, $0-24
@@ -27,7 +329,7 @@ TEXT ·add(SB), NOSPLIT, $0-24
 		t.Fatalf("assemble: %v", err)
 	}
 
-	ds := emitDWARF(img, "test_amd64.s")
+	ds := emitDWARF(img, "test_amd64.s", cfiAMD64)
 
 	// .debug_abbrev must not be empty and must start with abbrev code 1.
 	if len(ds.debugAbbrev) == 0 {
@@ -68,14 +370,3 @@ TEXT ·add(SB), NOSPLIT, $0-24
 		t.Fatal("no .debug_info relocations")
 	}
 }
-
-func TestDwarfAbbrevTable(t *testing.T) {
-	abbrev := dwarfAbbrevTable()
-	if len(abbrev) == 0 {
-		t.Fatal("empty abbrev table")
-	}
-	// Must end with a zero byte (end of table).
-	if abbrev[len(abbrev)-1] != 0 {
-		t.Fatalf("abbrev table last byte = %d, want 0", abbrev[len(abbrev)-1])
-	}
-}

asm/elf_test.go

@@ -12,6 +12,7 @@ import (
 	"path/filepath"
 	"testing"
 
+	"sourcedock.dev/petrbalvin/gasm-devkit/ast"
 	"sourcedock.dev/petrbalvin/gasm-devkit/parser"
 )
 
@@ -211,6 +212,75 @@ func TestELFObject(t *testing.T) {
 	}
 }
 
+// TestELFObjectTLSGuardReloc checks that a non-NOSPLIT function's stack
+// guard carries an R_X86_64_TPOFF32 relocation against the null symbol in
+// .rela.text.  The serialisation must honour the record's type field: a
+// hardcoded R_X86_64_PC32 mislinks the TLS load as an ordinary
+// PC-relative reference.
+func TestELFObjectTLSGuardReloc(t *testing.T) {
+	f, errs := parser.Parse("g_amd64.s", `
+#include "textflag.h"
+
+TEXT ·grow(SB), $0
+	CALL ·other(SB)
+	RET
+
+TEXT ·other(SB), NOSPLIT, $0
+	RET
+`)
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFile(f)
+	if err != nil {
+		t.Fatalf("AssembleFile: %v", err)
+	}
+	var haveTLS bool
+	for _, fn := range img.Funcs {
+		for _, r := range fn.Relocs {
+			if r.Kind == RelTLSLE {
+				haveTLS = true
+			}
+		}
+	}
+	if !haveTLS {
+		t.Fatal("test source produced no RelTLSLE relocation")
+	}
+	obj, err := img.ELFObject()
+	if err != nil {
+		t.Fatalf("ELFObject: %v", err)
+	}
+	ef, err := elf.NewFile(bytes.NewReader(obj))
+	if err != nil {
+		t.Fatalf("parse emitted object: %v", err)
+	}
+	defer ef.Close()
+	relaSec := ef.Section(".rela.text")
+	if relaSec == nil {
+		t.Fatal("missing .rela.text")
+	}
+	raw, err := relaSec.Data()
+	if err != nil {
+		t.Fatal(err)
+	}
+	found := false
+	for i := 0; i+24 <= len(raw); i += 24 {
+		e := raw[i:]
+		info := binary.LittleEndian.Uint64(e[8:])
+		typ := info & 0xffffffff
+		sym := int(info >> 32)
+		if typ == uint64(elf.R_X86_64_TPOFF32) {
+			found = true
+			if sym != 0 {
+				t.Errorf("TPOFF32 relocation against symbol %d, want 0 (the null symbol)", sym)
+			}
+		}
+	}
+	if !found {
+		t.Errorf("no R_X86_64_TPOFF32 relocation in .rela.text (%d bytes)", len(raw))
+	}
+}
+
 // TestELFObjectNoRelocations checks a file with no static-symbol references
 // emits a valid object without a .rela.text section.
 func TestELFObjectNoRelocations(t *testing.T) {
@@ -253,6 +323,238 @@ TEXT ·nop(SB), NOSPLIT, $0
 	}
 }
 
+// elfSectionHeaderCount returns the e_shnum the ELF header declares.
+func elfSectionHeaderCount(t *testing.T, obj []byte) int {
+	t.Helper()
+	return int(binary.LittleEndian.Uint16(obj[60:]))
+}
+
+// checkELFSectionAccounting verifies the number of section headers the
+// writer physically laid out equals e_shnum: every DWARF section written
+// after .shstrtab must be counted, or the last ones (always .debug_frame)
+// are invisible to every consumer, debug/elf included.
+func checkELFSectionAccounting(t *testing.T, obj []byte) {
+	t.Helper()
+	shoff := int(binary.LittleEndian.Uint64(obj[40:]))
+	shentsize := int(binary.LittleEndian.Uint16(obj[58:]))
+	shnum := elfSectionHeaderCount(t, obj)
+	if shentsize != 64 {
+		t.Fatalf("e_shentsize = %d, want 64", shentsize)
+	}
+	if (len(obj)-shoff)%shentsize != 0 {
+		t.Fatalf("section header table is not a whole number of entries: shoff=%d len=%d", shoff, len(obj))
+	}
+	if present := (len(obj) - shoff) / shentsize; present != shnum {
+		t.Errorf("e_shnum = %d but %d section headers are laid out", shnum, present)
+	}
+}
+
+// TestELFDWARFSectionAccounting runs the header accounting check over all
+// four architecture emitters, and additionally checks the .debug_frame
+// section is visible (its data aligned as its header declares).
+func TestELFDWARFSectionAccounting(t *testing.T) {
+	parse := func(name, src string) *ast.File {
+		f, errs := parser.Parse(name, src)
+		if len(errs) > 0 {
+			t.Fatalf("parse %s: %v", name, errs)
+		}
+		return f
+	}
+	cases := []struct {
+		name string
+		img  *Image
+		emit func(*Image) ([]byte, error)
+	}{
+		{"amd64", elfTestImage(t), (*Image).ELFObject},
+		{"arm64", mustImage(t, func() (*Image, error) {
+			return AssembleFileARM64(parse("k_arm64.s", `
+#include "textflag.h"
+
+TEXT ·add(SB), NOSPLIT, $0-24
+	MOVD a+0(FP), R4
+	MOVD b+8(FP), R5
+	ADD R5, R4, R4
+	MOVD R4, ret+16(FP)
+	RET
+`))
+		}), (*Image).ELFAARCH64Object},
+		{"riscv64", mustImage(t, func() (*Image, error) {
+			return AssembleFileRISCV(parse("k_riscv64.s", `
+#include "textflag.h"
+
+TEXT ·sb(SB), NOSPLIT, $0-0
+	MOV $answer<>(SB), X10
+	RET
+
+GLOBL answer<>(SB), RODATA, $8
+DATA answer<>+0(SB)/8, $42
+`))
+		}), (*Image).ELFRISCVObject},
+		{"loong64", mustImage(t, func() (*Image, error) {
+			return AssembleFileLOONG64(parse("k_loong64.s", `
+#include "textflag.h"
+
+TEXT ·add(SB), NOSPLIT, $0-24
+	MOVV a+0(FP), R4
+	MOVV b+8(FP), R5
+	ADDV R5, R4, R4
+	MOVV R4, ret+16(FP)
+	RET
+`))
+		}), (*Image).ELFLOONG64Object},
+	}
+	for _, tc := range cases {
+		obj, err := tc.emit(tc.img)
+		if err != nil {
+			t.Fatalf("%s: emit: %v", tc.name, err)
+		}
+		checkELFSectionAccounting(t, obj)
+		ef, err := elf.NewFile(bytes.NewReader(obj))
+		if err != nil {
+			t.Fatalf("%s: parse emitted object: %v", tc.name, err)
+		}
+		frame := ef.Section(".debug_frame")
+		if frame == nil {
+			t.Errorf("%s: .debug_frame invisible to debug/elf (e_shnum too small?)", tc.name)
+			ef.Close()
+			continue
+		}
+		if frame.Offset%8 != 0 || frame.Addralign != 8 {
+			t.Errorf("%s: .debug_frame offset %d align %d, want offset%%8==0 align 8", tc.name, frame.Offset, frame.Addralign)
+		}
+		ef.Close()
+	}
+}
+
+func mustImage(t *testing.T, f func() (*Image, error)) *Image {
+	t.Helper()
+	img, err := f()
+	if err != nil {
+		t.Fatal(err)
+	}
+	return img
+}
+
+// TestELFDWARFRelocations checks the .rela.debug_info and .rela.debug_line
+// sections exist and carry absolute 64-bit relocations against the
+// function symbols, with r_offsets inside their target sections.
+func TestELFDWARFRelocations(t *testing.T) {
+	img := elfTestImage(t)
+	obj, err := img.ELFObject()
+	if err != nil {
+		t.Fatalf("ELFObject: %v", err)
+	}
+	ef, err := elf.NewFile(bytes.NewReader(obj))
+	if err != nil {
+		t.Fatalf("parse emitted object: %v", err)
+	}
+	defer ef.Close()
+	// The DWARF must record the assembled file's path (threaded through
+	// Image.SourcePath), not a placeholder name.
+	info, err := ef.Section(".debug_info").Data()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if img.SourcePath != "t_amd64.s" || !bytes.Contains(info, []byte(img.SourcePath)) {
+		t.Errorf("DWARF compilation unit does not name the source %q", img.SourcePath)
+	}
+	for _, tc := range []struct {
+		rela   string
+		target string
+		want   uint32
+	}{
+		{".rela.debug_info", ".debug_info", rX8664Abs64},
+		{".rela.debug_line", ".debug_line", rX8664Abs64},
+		{".rela.debug_frame", ".debug_frame", rX8664Abs64},
+	} {
+		rs := ef.Section(tc.rela)
+		if rs == nil {
+			t.Fatalf("missing %s", tc.rela)
+		}
+		if rs.Type != elf.SHT_RELA {
+			t.Errorf("%s: type %v, want SHT_RELA", tc.rela, rs.Type)
+		}
+		target := ef.Section(tc.target)
+		if target == nil {
+			t.Fatalf("missing %s", tc.target)
+		}
+		if rs.Link == 0 || ef.Sections[rs.Info] != target {
+			t.Errorf("%s: link %d info %d, want the symtab and %s", tc.rela, rs.Link, rs.Info, tc.target)
+		}
+		b, err := rs.Data()
+		if err != nil {
+			t.Fatal(err)
+		}
+		// .debug_line has one address per function; .debug_info adds the
+		// compile unit's own low_pc.
+		want := len(img.Funcs)
+		if tc.target == ".debug_info" {
+			want++
+		}
+		if len(b)/24 != want {
+			t.Errorf("%s: %d entries, want %d", tc.rela, len(b)/24, want)
+		}
+		for i := 0; i+24 <= len(b); i += 24 {
+			r_offset := binary.LittleEndian.Uint64(b[i:])
+			info := binary.LittleEndian.Uint64(b[i+8:])
+			typ := uint32(info)
+			sym := int(info >> 32)
+			if typ != tc.want {
+				t.Errorf("%s entry %d: type %d, want R_X86_64_64 (%d)", tc.rela, i/24, typ, tc.want)
+			}
+			if r_offset >= uint64(target.Size) {
+				t.Errorf("%s entry %d: r_offset %d outside %s (%d bytes)", tc.rela, i/24, r_offset, tc.target, target.Size)
+			}
+			if sym == 0 {
+				t.Errorf("%s entry %d: against the null symbol", tc.rela, i/24)
+			}
+		}
+	}
+}
+
+// TestELFDataOnly checks a source with GLOBL data and no TEXT emits a valid
+// ELF object: the DWARF compilation unit of a code-less image has no
+// function to relocate against and must not reach for one.
+func TestELFDataOnly(t *testing.T) {
+	f, errs := parser.Parse("d0_amd64.s", `
+GLOBL table<>(SB), RODATA, $8
+DATA table<>+0(SB)/8, $12345
+`)
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFile(f)
+	if err != nil {
+		t.Fatalf("AssembleFile: %v", err)
+	}
+	obj, err := img.ELFObject()
+	if err != nil {
+		t.Fatalf("ELFObject: %v", err)
+	}
+	checkELFSectionAccounting(t, obj)
+	ef, err := elf.NewFile(bytes.NewReader(obj))
+	if err != nil {
+		t.Fatalf("parse emitted object: %v", err)
+	}
+	defer ef.Close()
+	syms, err := ef.Symbols()
+	if err != nil {
+		t.Fatal(err)
+	}
+	found := false
+	for _, s := range syms {
+		if s.Name == "table" && s.Size == 8 {
+			found = true
+		}
+	}
+	if !found {
+		t.Errorf("data symbol table missing: %v", syms)
+	}
+	if ef.Section(".rela.debug_info") != nil || ef.Section(".rela.debug_line") != nil {
+		t.Error("data-only image must not emit DWARF address relocations")
+	}
+}
+
 // TestELFLinkAndRun is the end-to-end check: assemble the test functions,
 // link the emitted object with a C driver that defines the external symbol,
 // and run the result.  Skipped when no C compiler is available.
@@ -307,4 +609,144 @@ int main(void) {
 	if got := string(run); got != "42 42 7\n" {
 		t.Errorf("output %q, want \"42 42 7\\n\"", got)
 	}
+
+	// The DWARF addresses must have resolved at link time: the .debug_info
+	// placeholders were carried by .rela.debug_info, so every subprogram's
+	// low_pc must now equal its linked symbol address.
+	bin, err := os.ReadFile(appPath)
+	if err != nil {
+		t.Fatal(err)
+	}
+	lef, err := elf.NewFile(bytes.NewReader(bin))
+	if err != nil {
+		t.Fatalf("parse linked binary: %v", err)
+	}
+	defer lef.Close()
+	syms, err := lef.Symbols()
+	if err != nil {
+		t.Fatal(err)
+	}
+	addrByName := map[string]uint64{}
+	for _, s := range syms {
+		if elf.ST_TYPE(s.Info) == elf.STT_FUNC && s.Value != 0 {
+			addrByName[s.Name] = s.Value
+		}
+	}
+	lowPCs := dwarfSubprogramLowPCs(t, lef)
+	if len(lowPCs) == 0 {
+		t.Fatal("no subprogram DW_AT_low_pc parsed from the linked binary")
+	}
+	for name, pc := range lowPCs {
+		addr, ok := addrByName[name]
+		if !ok {
+			t.Errorf("subprogram %q not in the linked symbol table", name)
+			continue
+		}
+		if pc != addr {
+			t.Errorf("subprogram %q: DW_AT_low_pc = %#x, linked address %#x (DWARF relocation unresolved)", name, pc, addr)
+		}
+	}
+}
+
+// dwarfSubprogramLowPCs walks the linked binary's .debug_info with its own
+// .debug_abbrev and returns each DW_TAG_subprogram's DW_AT_low_pc by name.
+func dwarfSubprogramLowPCs(t *testing.T, ef *elf.File) map[string]uint64 {
+	t.Helper()
+	abbrevSec := ef.Section(".debug_abbrev")
+	infoSec := ef.Section(".debug_info")
+	if abbrevSec == nil || infoSec == nil {
+		t.Fatal("linked binary lacks .debug_abbrev or .debug_info")
+	}
+	abbrev, err := abbrevSec.Data()
+	if err != nil {
+		t.Fatal(err)
+	}
+	info, err := infoSec.Data()
+	if err != nil {
+		t.Fatal(err)
+	}
+	abs := parseAbbrevs(t, abbrev)
+	le := binary.LittleEndian
+	out := map[string]uint64{}
+	r := &ulebIter{b: info}
+	r.uint32At(t) // unit_length
+	if v := le.Uint16(info[4:]); v != 5 {
+		t.Fatalf(".debug_info version %d, want 5", v)
+	}
+	r.i = 6
+	r.byteAt(t)   // unit_type
+	r.byteAt(t)   // address_size
+	r.uint32At(t) // debug_abbrev_offset
+	var name string
+	var lowPC uint64
+	for r.i < len(r.b) {
+		code := r.uleb(t)
+		if code == 0 {
+			continue // end of the CU's children
+		}
+		ab, ok := abs[code]
+		if !ok {
+			t.Fatalf("unknown abbreviation code %d", code)
+		}
+		name, lowPC = "", 0
+		for _, a := range ab.attrs {
+			switch a.attr {
+			case dwAtName:
+				readFormKeep(t, r, a.form, &name, nil)
+			case dwAtLowPC:
+				readFormKeep(t, r, a.form, nil, &lowPC)
+			default:
+				readFormSkip(t, r, a.form)
+			}
+		}
+		if ab.tag == dwTagSubprog && name != "" {
+			out[name] = lowPC
+		}
+	}
+	return out
+}
+
+// readFormKeep reads one DIE attribute value, keeping a string or an
+// address into the pointer it was given (nil keeps nothing).
+func readFormKeep(t *testing.T, r *ulebIter, form uint64, name *string, addr *uint64) {
+	t.Helper()
+	switch form {
+	case dwFormString:
+		end := r.i
+		for end < len(r.b) && r.b[end] != 0 {
+			end++
+		}
+		if name != nil {
+			*name = string(r.b[r.i:end])
+		}
+		r.i = end + 1
+	case dwFormAddr:
+		if addr != nil {
+			*addr = binary.LittleEndian.Uint64(r.b[r.i:])
+		}
+		r.i += 8
+	default:
+		readFormSkip(t, r, form)
+	}
+}
+
+func readFormSkip(t *testing.T, r *ulebIter, form uint64) {
+	t.Helper()
+	switch form {
+	case dwFormString:
+		for r.i < len(r.b) && r.b[r.i] != 0 {
+			r.i++
+		}
+		r.i++
+	case dwFormAddr, dwFormData8:
+		r.i += 8
+	case dwFormSecOff:
+		r.i += 4
+	case dwFormExprloc:
+		r.i += int(r.uleb(t))
+	case dwFormData1, 0x0c:
+		r.i++
+	default:
+		t.Fatalf("unsupported form %#x", form)
+	}
 }

asm/elfarm64.go

@@ -81,10 +81,15 @@ func (img *Image) ELFAARCH64Object() ([]byte, error) {
 	}
 
 	// Build relocations.  Each SB reference is an ADRP pair:
-	//   ADRP Rd, 0  → R_AARCH64_ADR_PREL_PG_HI21
-	//   ADD         → R_AARCH64_ADD_ABS_LO12_NC
-	//   LDR/STR X   → R_AARCH64_LDST64_ABS_LO12_NC
+	//   ADRP Rd, 0  → R_AARCH64_ADR_PREL_PG_HI21 at the ADRP
+	//   ADD         → R_AARCH64_ADD_ABS_LO12_NC at the ADD word
+	//   LDR/STR X   → R_AARCH64_LDST64_ABS_LO12_NC at the LDR/STR word
 	//   BL          → R_AARCH64_CALL26
+	// cmd/link's own conversion emits the HI21 at sectoff and the LO12 at
+	// sectoff+4 (cmd/link/internal/arm64/asm.go), so the ADD or load word
+	// carries the page-offset relocation, never a second HI21.  The
+	// assembler records two RelArm64Addr relocs per ADRP+ADD pair (one per
+	// word), so the second of the pair is consumed here.
 	// Addends stay raw: ADR_PREL_PG_HI21 and the ABS_LO12_NC forms resolve
 	// against S+A, and CALL26 branches take the branch instruction's own
 	// place as the PC-relative base, so subtracting the field width (the
@@ -97,28 +102,34 @@ func (img *Image) ELFAARCH64Object() ([]byte, error) {
 	}
 	var relas []elfRela
 	for _, fn := range img.Funcs {
-		for _, r := range fn.Relocs {
+		for i := 0; i < len(fn.Relocs); i++ {
+			r := fn.Relocs[i]
 			idx, ok := symIdx[r.Name]
 			if !ok {
 				return nil, fmt.Errorf("relocation references unknown symbol %q", r.Name)
 			}
-			var typ uint32
-			switch {
-			case r.Kind == RelArm64Branch:
-				typ = rArm64Call26
-			case r.Kind == RelArm64LDST64 && r.Off%4 == 4:
-				typ = rArm64Ldst64Lo12NC
-			case r.Kind == RelArm64Addr && r.Off%4 == 4:
-				typ = rArm64AddAbsLo12NC
+			switch r.Kind {
+			case RelArm64Branch:
+				relas = append(relas, elfRela{
+					off: uint64(fn.Offset + r.Off), typ: rArm64Call26, sym: idx, addend: r.Addend,
+				})
+			case RelArm64Addr:
+				// ADRP+ADD: the pair's second reloc (at Off+4) is the
+				// assembler's twin of the same pair; skip it.
+				relas = append(relas,
+					elfRela{off: uint64(fn.Offset + r.Off), typ: rArm64PrelPgHi21, sym: idx, addend: r.Addend},
+					elfRela{off: uint64(fn.Offset + r.Off + 4), typ: rArm64AddAbsLo12NC, sym: idx, addend: r.Addend},
+				)
+				i++
+			case RelArm64LDST64:
+				// ADRP+LDR/STR: one assembler reloc covers the pair.
+				relas = append(relas,
+					elfRela{off: uint64(fn.Offset + r.Off), typ: rArm64PrelPgHi21, sym: idx, addend: r.Addend},
+					elfRela{off: uint64(fn.Offset + r.Off + 4), typ: rArm64Ldst64Lo12NC, sym: idx, addend: r.Addend},
+				)
 			default:
-				typ = rArm64PrelPgHi21
+				return nil, fmt.Errorf("relocation kind %v unsupported in ELF emission", r.Kind)
 			}
-			relas = append(relas, elfRela{
-				off:    uint64(fn.Offset + r.Off),
-				typ:    typ,
-				sym:    idx,
-				addend: r.Addend,
-			})
 		}
 	}
 
@@ -193,15 +204,32 @@ func (img *Image) ELFAARCH64Object() ([]byte, error) {
 	shstrOff := len(out)
 	out = append(out, stSections.bytes()...)
 
-	// DWARF debug sections.
+	// DWARF debug sections; the address placeholders they leave are carried
+	// as .rela.debug_info/.rela.debug_line entries the system linker applies.
 	dwAlign := func(n int) {
 		for len(out)%n != 0 {
 			out = append(out, 0)
 		}
 	}
-	dw := appendDWARFSections(&out, img, "gasm.s", symIdx, dwAlign)
+	dw := appendDWARFSections(&out, img, dwarfSourceName(img), symIdx, dwAlign, cfiARM64)
+	dwarfStart := 0 // section index of .debug_abbrev, set when DWARF is present
 	if dw != nil {
-		nSections += 4
+		// Five DWARF sections: .debug_abbrev, .debug_info, .debug_line,
+		// .debug_line_str and .debug_frame (the CIE is unconditional, so
+		// the frame section is always present), plus the relocation
+		// sections below when they carry entries.
+		dwarfStart = nSections
+		nSections += 5
+		appendDWARFRelas(&out, dw, rAARCH64Abs64, dwAlign)
+		if dw.infoRelaCount > 0 {
+			nSections++
+		}
+		if dw.lineRelaCount > 0 {
+			nSections++
+		}
+		if dw.frameRelaCount > 0 {
+			nSections++
+		}
 	}
 
 	align(8)
@@ -230,13 +258,37 @@ func (img *Image) ELFAARCH64Object() ([]byte, error) {
 		putSh(".rela.text", shtRela, 0, relaOff, 24*len(relas), secSymtab, secText, 8, 24)
 	}
 	putSh(".shstrtab", shtStrtab, 0, shstrOff, len(stSections.bytes()), 0, 0, 1, 0)
+	// DWARF section headers; their indices follow the write order.
 	if dw != nil {
+		// secIdx is a running section index: each putSh below emits the
+		// next header, and the sh_info of a .rela section names the index
+		// of the section it relocates.
+		secIdx := dwarfStart
 		putSh(".debug_abbrev", shtProgbits, 0, dw.abbrevOff, dw.abbrevSize, 0, 0, 1, 0)
+		secIdx++
 		putSh(".debug_info", shtProgbits, 0, dw.infoOff, dw.infoSize, 0, 0, 1, 0)
+		secInfoIdx := secIdx
+		secIdx++
+		if dw.infoRelaCount > 0 {
+			putSh(".rela.debug_info", shtRela, 0, dw.infoRelaOff, 24*dw.infoRelaCount, secSymtab, secInfoIdx, 8, 24)
+			secIdx++
+		}
 		putSh(".debug_line", shtProgbits, 0, dw.lineOff, dw.lineSize, 0, 0, 1, 0)
+		secLineIdx := secIdx
+		secIdx++
+		if dw.lineRelaCount > 0 {
+			putSh(".rela.debug_line", shtRela, 0, dw.lineRelaOff, 24*dw.lineRelaCount, secSymtab, secLineIdx, 8, 24)
+			secIdx++
+		}
 		putSh(".debug_line_str", shtProgbits, 0, dw.lineStrOff, dw.lineStrSize, 0, 0, 1, 0)
+		secIdx++
 		if dw.frameSize > 0 {
 			putSh(".debug_frame", shtProgbits, 0, dw.frameOff, dw.frameSize, 0, 0, 8, 0)
+			secFrameIdx := secIdx
+			secIdx++
+			if dw.frameRelaCount > 0 {
+				putSh(".rela.debug_frame", shtRela, 0, dw.frameRelaOff, 24*dw.frameRelaCount, secSymtab, secFrameIdx, 8, 24)
+			}
 		}
 	}
 

asm/elfarm64_test.go

@@ -6,6 +6,7 @@ package asm
 import (
 	"bytes"
 	"debug/elf"
+	"encoding/binary"
 	"testing"
 
 	"sourcedock.dev/petrbalvin/gasm-devkit/parser"
@@ -28,6 +29,7 @@ TEXT ·add(SB), NOSPLIT, $0-24
 
 TEXT ·getanswer(SB), NOSPLIT, $0-8
 	MOVD answer<>(SB), R4
+	MOVD $answer<>(SB), R5
 	MOVD R4, ret+0(FP)
 	RET
 
@@ -102,8 +104,63 @@ DATA answer<>+0(SB)/8, $42
 	// Check that .rela.text exists (getanswer has SB reference).
 	relaText := ef.Section(".rela.text")
 	if relaText == nil {
-		t.Error("missing .rela.text section")
+		t.Fatal("missing .rela.text section")
 	}
+
+	// The SB references of getanswer form two ADRP pairs: the load
+	// (MOVD answer<>(SB), R4) is ADRP+LDR carrying HI21 at the ADRP and
+	// LDST64_ABS_LO12_NC at the LDR word, and the address-of
+	// (MOVD $answer<>(SB), R5) is ADRP+ADD carrying HI21 and
+	// ADD_ABS_LO12_NC.  cmd/link's own conversion emits exactly this
+	// sectoff / sectoff+4 pairing; a second HI21 at the ADD or LDR word
+	// corrupts the pair.
+	raw, err := relaText.Data()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(raw)%24 != 0 || len(raw)/24 != 4 {
+		t.Fatalf(".rela.text has %d bytes, want four 24-byte entries", len(raw))
+	}
+	wantRela := []struct {
+		typ elf.R_AARCH64
+		off uint64 // relative to the getanswer function start
+	}{
+		{elf.R_AARCH64_ADR_PREL_PG_HI21, 0},
+		{elf.R_AARCH64_LDST64_ABS_LO12_NC, 4},
+		{elf.R_AARCH64_ADR_PREL_PG_HI21, 8},
+		{elf.R_AARCH64_ADD_ABS_LO12_NC, 12},
+	}
+	getanswer := byNameElf(t, ef, "getanswer")
+	for i, w := range wantRela {
+		e := raw[i*24 : (i+1)*24]
+		off := binary.LittleEndian.Uint64(e[0:])
+		info := binary.LittleEndian.Uint64(e[8:])
+		typ := elf.R_AARCH64(info & 0xffffffff)
+		sym := int(info >> 32)
+		if typ != w.typ || off != getanswer.Value+w.off {
+			t.Errorf("reloc %d: type %v off %d, want %v at %d", i, typ, off, w.typ, getanswer.Value+w.off)
+		}
+		if sym != 3 { // NULL, .text, .data, then the first local: answer
+			t.Errorf("reloc %d: symbol index %d, want 3 (answer)", i, sym)
+		}
+	}
+}
+
+// byNameElf returns the symbol table entry for name from the raw .symtab,
+// which carries every entry including the null and section symbols in order.
+func byNameElf(t *testing.T, ef *elf.File, name string) elf.Symbol {
+	t.Helper()
+	syms, err := ef.Symbols()
+	if err != nil {
+		t.Fatalf("symbols: %v", err)
+	}
+	for _, s := range syms {
+		if s.Name == name {
+			return s
+		}
+	}
+	t.Fatalf("symbol %q not found", name)
+	return elf.Symbol{}
 }
 
 // TestELFAARCH64ObjectNoRelocations checks the ELF output when there are no

asm/elfloong64.go

@@ -13,6 +13,12 @@ import (
 const (
 	emLOONGARCH = 258 // EM_LOONGARCH
 
+	// EF_LOONGARCH_ABI_DOUBLE_FLOAT | EF_LOONGARCH_OBJABI_V1: the flags the
+	// Go toolchain writes (cmd/link/internal/ld/elf.go: Flags = 0x43 for
+	// Loong64).  System linkers refuse to merge ET_REL objects whose float
+	// ABI differs, so 0 (soft-float) would make the object unlinkable.
+	efLarchAbiDoubleObjV1 = 0x43
+
 	// LoongArch relocation types (the ELF psABI).
 	rLarchPCALAHI20 = 71 // R_LARCH_PCALA_HI20 (pcalau12i)
 	rLarchPCALALO12 = 72 // R_LARCH_PCALA_LO12 (addi.d/ld/st)
@@ -187,9 +193,25 @@ func (img *Image) ELFLOONG64Object() ([]byte, error) {
 			out = append(out, 0)
 		}
 	}
-	dw := appendDWARFSections(&out, img, "gasm.s", symIdx, dwAlign)
+	dw := appendDWARFSections(&out, img, dwarfSourceName(img), symIdx, dwAlign, cfiLOONG64)
+	dwarfStart := 0 // section index of .debug_abbrev, set when DWARF is present
 	if dw != nil {
-		nSections += 4
+		// Five DWARF sections: .debug_abbrev, .debug_info, .debug_line,
+		// .debug_line_str and .debug_frame (the CIE is unconditional, so
+		// the frame section is always present), plus the relocation
+		// sections below when they carry entries.
+		dwarfStart = nSections
+		nSections += 5
+		appendDWARFRelas(&out, dw, rLarchAbs64, dwAlign)
+		if dw.infoRelaCount > 0 {
+			nSections++
+		}
+		if dw.lineRelaCount > 0 {
+			nSections++
+		}
+		if dw.frameRelaCount > 0 {
+			nSections++
+		}
 	}
 
 	align(8)
@@ -218,13 +240,37 @@ func (img *Image) ELFLOONG64Object() ([]byte, error) {
 		putSh(".rela.text", shtRela, 0, relaOff, 24*len(relas), secSymtab, secText, 8, 24)
 	}
 	putSh(".shstrtab", shtStrtab, 0, shstrOff, len(stSections.bytes()), 0, 0, 1, 0)
+	// DWARF section headers; their indices follow the write order.
 	if dw != nil {
+		// secIdx is a running section index: each putSh below emits the
+		// next header, and the sh_info of a .rela section names the index
+		// of the section it relocates.
+		secIdx := dwarfStart
 		putSh(".debug_abbrev", shtProgbits, 0, dw.abbrevOff, dw.abbrevSize, 0, 0, 1, 0)
+		secIdx++
 		putSh(".debug_info", shtProgbits, 0, dw.infoOff, dw.infoSize, 0, 0, 1, 0)
+		secInfoIdx := secIdx
+		secIdx++
+		if dw.infoRelaCount > 0 {
+			putSh(".rela.debug_info", shtRela, 0, dw.infoRelaOff, 24*dw.infoRelaCount, secSymtab, secInfoIdx, 8, 24)
+			secIdx++
+		}
 		putSh(".debug_line", shtProgbits, 0, dw.lineOff, dw.lineSize, 0, 0, 1, 0)
+		secLineIdx := secIdx
+		secIdx++
+		if dw.lineRelaCount > 0 {
+			putSh(".rela.debug_line", shtRela, 0, dw.lineRelaOff, 24*dw.lineRelaCount, secSymtab, secLineIdx, 8, 24)
+			secIdx++
+		}
 		putSh(".debug_line_str", shtProgbits, 0, dw.lineStrOff, dw.lineStrSize, 0, 0, 1, 0)
+		secIdx++
 		if dw.frameSize > 0 {
 			putSh(".debug_frame", shtProgbits, 0, dw.frameOff, dw.frameSize, 0, 0, 8, 0)
+			secFrameIdx := secIdx
+			secIdx++
+			if dw.frameRelaCount > 0 {
+				putSh(".rela.debug_frame", shtRela, 0, dw.frameRelaOff, 24*dw.frameRelaCount, secSymtab, secFrameIdx, 8, 24)
+			}
 		}
 	}
 
@@ -237,7 +283,7 @@ func (img *Image) ELFLOONG64Object() ([]byte, error) {
 	le.PutUint64(hdr[24:], 0)
 	le.PutUint64(hdr[32:], 0)
 	le.PutUint64(hdr[40:], uint64(shoff))
-	le.PutUint32(hdr[48:], 0)
+	le.PutUint32(hdr[48:], efLarchAbiDoubleObjV1)
 	le.PutUint16(hdr[52:], 64)
 	le.PutUint16(hdr[54:], 0)
 	le.PutUint16(hdr[56:], 0)

asm/elfloong64_test.go

@@ -55,6 +55,11 @@ DATA answer<>+0(SB)/8, $42
 	if ef.Type != elf.ET_REL || ef.Machine != elf.EM_LOONGARCH {
 		t.Errorf("type/machine = %v/%v, want ET_REL/EM_LOONGARCH", ef.Type, ef.Machine)
 	}
+	// The double-float ABI plus OBJABI_V1 flags the Go toolchain writes;
+	// system linkers refuse ABI-mismatched merges.
+	if flags := binary.LittleEndian.Uint32(obj[48:]); flags != efLarchAbiDoubleObjV1 {
+		t.Errorf("e_flags = %#x, want %#x (double-float, OBJABI_V1)", flags, efLarchAbiDoubleObjV1)
+	}
 
 	text := ef.Section(".text")
 	data := ef.Section(".data")

asm/elfriscv.go

@@ -13,8 +13,13 @@ import (
 const (
 	emRISCV = 243 // EM_RISCV
 
+	// EF_RISCV_FLOAT_ABI_DOUBLE: the double-precision float ABI the Go
+	// toolchain targets (cmd/link/internal/ld/elf.go writes Flags = 0x4 for
+	// RISCV64).  System linkers refuse to merge ET_REL objects whose float
+	// ABI differs, so 0 (soft-float) would make the object unlinkable.
+	efRISCVFloatAbiDouble = 0x4
+
 	// RISC-V relocation types.
-	rRISCV32         = 1
 	rRISCVJAL        = 17 // R_RISCV_JAL
 	rRISCVPCRELHI20  = 23 // R_RISCV_PCREL_HI20
 	rRISCVPCRELLO12I = 24 // R_RISCV_PCREL_LO12_I
@@ -83,9 +88,14 @@ func (img *Image) ELFRISCVObject() ([]byte, error) {
 	// Build relocations.  Each SB reference is an AUIPC + second-instruction
 	// pair carrying a single relocation kind; the ELF writer expands it into
 	// the R_RISCV_PCREL_HI20 + R_RISCV_PCREL_LO12_I/S pair the psABI expects.
-	// The HI20 carries the symbol addend; the LO12 addend is zero, matching
-	// cmd/link's own ELF conversion (the LO12 resolves against the HI20's
-	// AUIPC location).
+	// The HI20 carries the symbol and its addend.  The LO12's symbol must
+	// denote the AUIPC site the HI20 relocates (psABI §8.4.9: the pair is
+	// resolved against the label of the AUIPC, not the target symbol;
+	// cmd/link generates one local text symbol per AUIPC for exactly this,
+	// cmd/link/internal/riscv64/asm.go).  The .text section symbol with the
+	// AUIPC's section-relative offset as addend gives S + A = the AUIPC
+	// address, which is that label.
+	const secSymText = 1 // syms[1], the .text section symbol
 	type elfRela struct {
 		off    uint64
 		typ    uint32
@@ -99,21 +109,20 @@ func (img *Image) ELFRISCVObject() ([]byte, error) {
 			if !ok {
 				return nil, fmt.Errorf("relocation references unknown symbol %q", r.Name)
 			}
+			auipc := int64(fn.Offset + r.Off)
 			switch r.Kind {
 			case RelRISCVPCRELIType:
 				relas = append(relas,
 					elfRela{off: uint64(fn.Offset + r.Off), typ: rRISCVPCRELHI20, sym: idx, addend: r.Addend},
-					elfRela{off: uint64(fn.Offset + r.Off + 4), typ: rRISCVPCRELLO12I, sym: idx, addend: 0},
+					elfRela{off: uint64(fn.Offset + r.Off + 4), typ: rRISCVPCRELLO12I, sym: secSymText, addend: auipc},
 				)
 			case RelRISCVPCRELSType:
 				relas = append(relas,
 					elfRela{off: uint64(fn.Offset + r.Off), typ: rRISCVPCRELHI20, sym: idx, addend: r.Addend},
-					elfRela{off: uint64(fn.Offset + r.Off + 4), typ: rRISCVPCRELLO12S, sym: idx, addend: 0},
+					elfRela{off: uint64(fn.Offset + r.Off + 4), typ: rRISCVPCRELLO12S, sym: secSymText, addend: auipc},
 				)
 			case RelRISCVJal:
 				relas = append(relas, elfRela{off: uint64(fn.Offset + r.Off), typ: rRISCVJAL, sym: idx, addend: r.Addend})
-			case RelPCRelAbs:
-				relas = append(relas, elfRela{off: uint64(fn.Offset + r.Off), typ: rRISCV32, sym: idx, addend: r.Addend})
 			default:
 				return nil, fmt.Errorf("relocation kind %v unsupported in ELF emission", r.Kind)
 			}
@@ -196,9 +205,25 @@ func (img *Image) ELFRISCVObject() ([]byte, error) {
 			out = append(out, 0)
 		}
 	}
-	dw := appendDWARFSections(&out, img, "gasm.s", symIdx, dwAlign)
+	dw := appendDWARFSections(&out, img, dwarfSourceName(img), symIdx, dwAlign, cfiRISCV64)
+	dwarfStart := 0 // section index of .debug_abbrev, set when DWARF is present
 	if dw != nil {
-		nSections += 4
+		// Five DWARF sections: .debug_abbrev, .debug_info, .debug_line,
+		// .debug_line_str and .debug_frame (the CIE is unconditional, so
+		// the frame section is always present), plus the relocation
+		// sections below when they carry entries.
+		dwarfStart = nSections
+		nSections += 5
+		appendDWARFRelas(&out, dw, rRISCVAbs64, dwAlign)
+		if dw.infoRelaCount > 0 {
+			nSections++
+		}
+		if dw.lineRelaCount > 0 {
+			nSections++
+		}
+		if dw.frameRelaCount > 0 {
+			nSections++
+		}
 	}
 
 	align(8)
@@ -227,13 +252,37 @@ func (img *Image) ELFRISCVObject() ([]byte, error) {
 		putSh(".rela.text", shtRela, 0, relaOff, 24*len(relas), secSymtab, secText, 8, 24)
 	}
 	putSh(".shstrtab", shtStrtab, 0, shstrOff, len(stSections.bytes()), 0, 0, 1, 0)
+	// DWARF section headers; their indices follow the write order.
 	if dw != nil {
+		// secIdx is a running section index: each putSh below emits the
+		// next header, and the sh_info of a .rela section names the index
+		// of the section it relocates.
+		secIdx := dwarfStart
 		putSh(".debug_abbrev", shtProgbits, 0, dw.abbrevOff, dw.abbrevSize, 0, 0, 1, 0)
+		secIdx++
 		putSh(".debug_info", shtProgbits, 0, dw.infoOff, dw.infoSize, 0, 0, 1, 0)
+		secInfoIdx := secIdx
+		secIdx++
+		if dw.infoRelaCount > 0 {
+			putSh(".rela.debug_info", shtRela, 0, dw.infoRelaOff, 24*dw.infoRelaCount, secSymtab, secInfoIdx, 8, 24)
+			secIdx++
+		}
 		putSh(".debug_line", shtProgbits, 0, dw.lineOff, dw.lineSize, 0, 0, 1, 0)
+		secLineIdx := secIdx
+		secIdx++
+		if dw.lineRelaCount > 0 {
+			putSh(".rela.debug_line", shtRela, 0, dw.lineRelaOff, 24*dw.lineRelaCount, secSymtab, secLineIdx, 8, 24)
+			secIdx++
+		}
 		putSh(".debug_line_str", shtProgbits, 0, dw.lineStrOff, dw.lineStrSize, 0, 0, 1, 0)
+		secIdx++
 		if dw.frameSize > 0 {
 			putSh(".debug_frame", shtProgbits, 0, dw.frameOff, dw.frameSize, 0, 0, 8, 0)
+			secFrameIdx := secIdx
+			secIdx++
+			if dw.frameRelaCount > 0 {
+				putSh(".rela.debug_frame", shtRela, 0, dw.frameRelaOff, 24*dw.frameRelaCount, secSymtab, secFrameIdx, 8, 24)
+			}
 		}
 	}
 
@@ -246,7 +295,7 @@ func (img *Image) ELFRISCVObject() ([]byte, error) {
 	le.PutUint64(hdr[24:], 0)
 	le.PutUint64(hdr[32:], 0)
 	le.PutUint64(hdr[40:], uint64(shoff))
-	le.PutUint32(hdr[48:], 0)
+	le.PutUint32(hdr[48:], efRISCVFloatAbiDouble)
 	le.PutUint16(hdr[52:], 64)
 	le.PutUint16(hdr[54:], 0)
 	le.PutUint16(hdr[56:], 0)

asm/encodable.go

@@ -36,10 +36,15 @@ func Encodable(mnemonic string) bool {
 	}
 
 	// CMOV carries size then condition (CMOVLGT); SET carries the condition
-	// alone (SETNE).
+	// alone (SETNE).  The size letter is checked exactly as encodeCmov does,
+	// so a spelling like CMOVBGT is not reported encodable when Encode
+	// would reject it.
 	if rest, ok := strings.CutPrefix(upper, "CMOV"); ok && len(rest) >= 2 {
-		if _, ok := jccMap[rest[1:]]; ok {
-			return true
+		switch rest[0] {
+		case 'W', 'L', 'Q':
+			if _, ok := jccMap[rest[1:]]; ok {
+				return true
+			}
 		}
 	}
 	if rest, ok := strings.CutPrefix(upper, "SET"); ok {
@@ -81,9 +86,16 @@ func Encodable(mnemonic string) bool {
 		"BSWAP",
 		"PREFETCHNTA", "PREFETCHT0", "PREFETCHT1", "PREFETCHT2",
 		"MOVBLZX", "MOVBQZX", "MOVWLZX", "MOVWQZX", "MOVWLSX", "MOVLQSX",
+		"MOVBWZX", "MOVBWSX", "MOVBLSX", "MOVBQSX", "MOVWQSX", "MOVLQZX",
 		"CVTSL2SD", "CVTSQ2SD",
 		"MOVOU", "MOVO", "MOVUPS", "MOVAPS", "MOVUPD", "MOVAPD", "MOVSD", "MOVSS":
 		return true
 	}
+	// Full-name dispatches the size split would eat (a trailing width
+	// letter that is part of the mnemonic).
+	switch upper {
+	case "PMOVMSKB":
+		return true
+	}
 	return false
 }

asm/encode.go

@@ -101,6 +101,11 @@ func (e *enc) encode(mnem string, ops []Operand) error {
 	if m, ok := sseBinTable[base]; ok {
 		return e.encodeSSEBin(m, ops)
 	}
+	// PMOVMSKB ends in a width letter the size split would eat, so it
+	// dispatches on the full name like the packed binaries above.
+	if upper == "PMOVMSKB" {
+		return e.encodePmovmskb(upper, ops)
+	}
 	switch base {
 	case "MOV":
 		return e.encodeMov(ops, size)
@@ -117,16 +122,17 @@ func (e *enc) encode(mnem string, ops []Operand) error {
 	case "IMUL", "IMUL3":
 		return e.encodeImul(ops, size)
 	case "PUSH":
-		return e.encodePushPop(ops, true)
+		return e.encodePushPop(ops, size, true)
 	case "POP":
-		return e.encodePushPop(ops, false)
+		return e.encodePushPop(ops, size, false)
 	case "BSF", "BSR", "LZCNT", "TZCNT", "POPCNT":
 		return e.encodeCount(base, ops, size)
 	case "BSWAP":
 		return e.encodeBswap(ops, size)
 	case "PREFETCHNTA", "PREFETCHT0", "PREFETCHT1", "PREFETCHT2":
 		return e.encodePrefetch(base, ops)
-	case "MOVBLZX", "MOVBQZX", "MOVWLZX", "MOVWQZX", "MOVWLSX", "MOVLQSX":
+	case "MOVBLZX", "MOVBQZX", "MOVWLZX", "MOVWQZX", "MOVWLSX", "MOVLQSX",
+		"MOVBWZX", "MOVBWSX", "MOVBLSX", "MOVBQSX", "MOVWQSX", "MOVLQZX":
 		return e.encodeMovExtend(base, ops)
 	case "CVTSL2SD", "CVTSQ2SD":
 		return e.encodeCvtsi2sd(base == "CVTSQ2SD", ops)
@@ -345,6 +351,12 @@ func setMem(i *instr, regField int, m Mem) error {
 // a memory operand.  It is shared by the REX (scalar) and VEX (vector) paths.
 func memComponents(regField int, m Mem) (modrm, sib int, disp []byte, xBit, bBit int, err error) {
 	sib = -1
+	// A displacement wider than int32 fits no encoding form; truncating it
+	// would address a different location, and go tool asm reports "offset
+	// too large" for the same operand.
+	if m.Disp < -(1<<31) || m.Disp > (1<<31)-1 {
+		return 0, -1, nil, 0, 0, fmt.Errorf("displacement %d does not fit in 32 bits", m.Disp)
+	}
 	// RIP-relative: neither base nor index.
 	if !m.HasBase && !m.HasIndex {
 		return regField<<3 | 0x05, -1, le32(m.Disp), 0, 0, nil // mod=00, rm=101

asm/encode_test.go

@@ -149,6 +149,45 @@ func TestPushPop(t *testing.T) {
 	checkSyntax(t, "push rbx", "PUSHQ", BX)
 	checkSyntax(t, "pop r12", "POPQ", Reg{idx: 12, size: 8})
 	checkSyntax(t, "push 0x5", "PUSHQ", Imm(5))
+	// The W spelling carries the 0x66 operand-size prefix, byte for byte
+	// with go tool asm; the L and B spellings are illegal in 64-bit mode
+	// there and rejected here rather than silently widened.
+	cases := []struct {
+		name string
+		mnem string
+		ops  []Operand
+		want string
+	}{
+		{"PUSHW AX", "PUSHW", []Operand{AX}, "6650"},
+		{"POPW AX", "POPW", []Operand{AX}, "6658"},
+		{"PUSHW $5", "PUSHW", []Operand{Imm(5)}, "666a05"},
+		{"PUSHW (AX)", "PUSHW", []Operand{Ptr(AX, 0, 2)}, "66ff30"},
+		{"PUSHQ AX", "PUSHQ", []Operand{AX}, "50"},
+	}
+	for _, c := range cases {
+		code, err := Encode(c.mnem, c.ops...)
+		if err != nil {
+			t.Errorf("%s: %v", c.name, err)
+			continue
+		}
+		if got := fmt.Sprintf("%x", code); got != c.want {
+			t.Errorf("%s: bytes %s, want %s", c.name, got, c.want)
+		}
+	}
+	for _, c := range []struct {
+		name string
+		mnem string
+		ops  []Operand
+	}{
+		{"PUSHL AX", "PUSHL", []Operand{AX}},
+		{"PUSHL R8", "PUSHL", []Operand{Reg{idx: 8, size: 8}}},
+		{"POPL BX", "POPL", []Operand{BX}},
+		{"PUSHB AX", "PUSHB", []Operand{AX}},
+	} {
+		if _, err := Encode(c.mnem, c.ops...); err == nil {
+			t.Errorf("%s: expected an error, got none", c.name)
+		}
+	}
 }
 
 func TestUnary(t *testing.T) {
@@ -318,6 +357,18 @@ func TestScalarGroundTruth(t *testing.T) {
 		{"MOVBQZX AL,R8", "MOVBQZX", []Operand{AL, r8}, "4c0fb6c0", "MOVZX"},
 		{"MOVWLZX AX,CX", "MOVWLZX", []Operand{AX, CX}, "0fb7c8", "MOVZX"},
 		{"MOVWQZX AX,R8", "MOVWQZX", []Operand{AX, r8}, "4c0fb7c0", "MOVZX"},
+		// The width pairs the toolchain accepts and GOROOT uses; bytes
+		// pinned from go tool asm (see testdata/verify/widen_amd64.s).
+		{"MOVBWZX (BX),R11W", "MOVBWZX", []Operand{Ptr(BX, 0, 1), Reg{idx: 11, size: 2}}, "66440fb61b", "MOVZX"},
+		{"MOVBWSX (BX),R11W", "MOVBWSX", []Operand{Ptr(BX, 0, 1), Reg{idx: 11, size: 2}}, "66440fbe1b", "MOVSX"},
+		{"MOVBLSX (BX),AX", "MOVBLSX", []Operand{Ptr(BX, 0, 1), AX}, "0fbe03", "MOVSX"},
+		{"MOVBQSX (BX),R8", "MOVBQSX", []Operand{Ptr(BX, 0, 1), r8}, "4c0fbe03", "MOVSX"},
+		{"MOVWQSX (BX),R9", "MOVWQSX", []Operand{Ptr(BX, 0, 2), r9}, "4c0fbf0b", "MOVSX"},
+		// A long to quad zero-extend is a plain 32-bit move.
+		{"MOVLQZX (BX),DX", "MOVLQZX", []Operand{Ptr(BX, 0, 4), DX}, "8b13", "MOV"},
+		{"MOVLQZX AX,DX", "MOVLQZX", []Operand{AX, DX}, "8bd0", "MOV"},
+		{"PMOVMSKB X1,AX", "PMOVMSKB", []Operand{vreg(t, "X1"), AX}, "660fd7c1", "PMOVMSKB"},
+		{"PMOVMSKB X11,CX", "PMOVMSKB", []Operand{vreg(t, "X11"), CX}, "66410fd7cb", "PMOVMSKB"},
 		{"CVTSL2SD R8,X13", "CVTSL2SD", []Operand{r8, vreg(t, "X13")}, "f2450f2ae8", "CVTSI2SD"},
 		{"CVTSL2SD AX,X0", "CVTSL2SD", []Operand{AX, vreg(t, "X0")}, "f20f2ac0", "CVTSI2SD"},
 		{"CVTSQ2SD R8,X13", "CVTSQ2SD", []Operand{r8, vreg(t, "X13")}, "f24d0f2ae8", "CVTSI2SD"},
@@ -397,6 +448,104 @@ func TestScalarErrors(t *testing.T) {
 	}
 }
 
+// TestImmediateOutOfRange pins the go-tool-asm parity of the immediate and
+// displacement spans: a scalar immediate must fit a signed or unsigned 32-bit
+// word (only MOVQ reg, $imm takes the full int64), a scalar shift count must
+// be an unsigned byte, and a displacement must fit int32.  Every rejected
+// shape here is rejected by `go tool asm` too; every accepted one encodes the
+// same bytes.
+func TestImmediateOutOfRange(t *testing.T) {
+	cases := []struct {
+		name string
+		mnem string
+		ops  []Operand
+	}{
+		{"SHLQ count 300", "SHLQ", []Operand{Imm(300), AX}},
+		{"SHLQ count -1", "SHLQ", []Operand{Imm(-1), AX}},
+		{"SHLW count 256", "SHLW", []Operand{Imm(256), DX}},
+		{"SHLB count 300", "SHLB", []Operand{Imm(300), BL}},
+		{"MOVL imm32+", "MOVL", []Operand{Imm(4294967296), AX}},
+		{"MOVL imm32-", "MOVL", []Operand{Imm(-2147483649), AX}},
+		{"MOVW imm32+", "MOVW", []Operand{Imm(4294967296), AX}},
+		{"MOVB imm32+", "MOVB", []Operand{Imm(4294967296), AL}},
+		{"ADDB imm32+", "ADDB", []Operand{Imm(4294967296), AL}},
+		{"ADDL imm32+", "ADDL", []Operand{Imm(4294967296), AX}},
+		{"ADDQ imm32+", "ADDQ", []Operand{Imm(8589934592), AX}},
+		{"CMPQ imm32+", "CMPQ", []Operand{AX, Imm(4294967296)}},
+		{"CMPQ imm32-", "CMPQ", []Operand{AX, Imm(-2147483649)}},
+		{"TESTL imm32+", "TESTL", []Operand{Imm(4294967296), AX}},
+		{"IMUL3L imm32+", "IMUL3L", []Operand{Imm(4294967296), CX, DX}},
+		{"PUSHQ imm32+", "PUSHQ", []Operand{Imm(4294967296)}},
+		{"MOVQ mem imm32+", "MOVQ", []Operand{Imm(4294967296), Ptr(AX, 0, 8)}},
+		{"disp32+", "MOVQ", []Operand{Ptr(AX, 4294967296, 8), BX}},
+		{"disp32+ max", "MOVQ", []Operand{Ptr(AX, 2147483648, 8), BX}},
+		{"disp32-", "MOVQ", []Operand{Ptr(AX, -2147483649, 8), BX}},
+		{"VEX disp32+", "VMOVDQU", []Operand{Ptr(AX, 4294967296, 32), vreg(t, "Y1")}},
+		{"EVEX disp32+", "VMOVDQU32", []Operand{Ptr(AX, 4294967296, 64), vreg(t, "Z1")}},
+	}
+	for _, c := range cases {
+		if _, err := Encode(c.mnem, c.ops...); err == nil {
+			t.Errorf("%s: expected an error, got none", c.name)
+		}
+	}
+}
+
+// TestImmediateTruncation pins the toolchain-matching truncations inside the
+// accepted 32-bit span: the narrower fields take the low bits silently, byte
+// for byte with `go tool asm` (which rejects none of these).
+func TestImmediateTruncation(t *testing.T) {
+	cases := []struct {
+		name string
+		mnem string
+		ops  []Operand
+		want string
+	}{
+		{"ADDB $256,BL", "ADDB", []Operand{Imm(256), BL}, "80c300"},
+		{"ADDB $1000,BL", "ADDB", []Operand{Imm(1000), BL}, "80c3e8"},
+		{"MOVB $256,AL", "MOVB", []Operand{Imm(256), AL}, "b000"},
+		{"MOVB $-129,AL", "MOVB", []Operand{Imm(-129), AL}, "b07f"},
+		{"MOVW $65536,AX", "MOVW", []Operand{Imm(65536), AX}, "66b80000"},
+		{"MOVW $65535,AX", "MOVW", []Operand{Imm(65535), AX}, "66b8ffff"},
+		{"MOVW $-32769,AX", "MOVW", []Operand{Imm(-32769), AX}, "66b8ff7f"},
+		{"MOVL $4294967295,AX", "MOVL", []Operand{Imm(4294967295), AX}, "b8ffffffff"},
+		{"ADDQ $4294967295,AX", "ADDQ", []Operand{Imm(4294967295), AX}, "4805ffffffff"},
+		{"CMPB BL,$255", "CMPB", []Operand{BL, Imm(255)}, "80fbff"},
+		{"CMPQ AX,$4294967295", "CMPQ", []Operand{AX, Imm(4294967295)}, "483dffffffff"},
+		{"MOVQ $4294967295,0(AX)", "MOVQ", []Operand{Imm(4294967295), Ptr(AX, 0, 8)}, "48c700ffffffff"},
+		{"SHLQ $255,AX", "SHLQ", []Operand{Imm(255), AX}, "48c1e0ff"},
+		{"SHLQ $0,AX", "SHLQ", []Operand{Imm(0), AX}, "48c1e000"},
+		// The one form beyond the 32-bit span: the imm64 MOVQ register move.
+		{"MOVQ $4294967296,AX", "MOVQ", []Operand{Imm(4294967296), AX}, "48b80000000001000000"},
+		{"MOVQ disp32 max", "MOVQ", []Operand{Ptr(AX, 2147483647, 8), BX}, "488b98ffffff7f"},
+	}
+	for _, c := range cases {
+		code, err := Encode(c.mnem, c.ops...)
+		if err != nil {
+			t.Errorf("%s: %v", c.name, err)
+			continue
+		}
+		if got := fmt.Sprintf("%x", code); got != c.want {
+			t.Errorf("%s: bytes %s, want %s", c.name, got, c.want)
+		}
+	}
+}
+
+// TestEncodableCmovSize pins the linter contract for CMOVcc: Encodable must
+// reject the spellings Encode rejects, so a mnemonic like CMOVBGT (no size
+// letter) is not reported as encodable.
+func TestEncodableCmovSize(t *testing.T) {
+	for _, m := range []string{"CMOVBGT", "CMOVXEQ", "CMOVB", "CMOV", "CMOVWXX"} {
+		if Encodable(m) {
+			t.Errorf("Encodable(%q) = true, want false", m)
+		}
+	}
+	for _, m := range []string{"CMOVLGT", "CMOVQGT", "CMOVWLS", "CMOVLEQ"} {
+		if !Encodable(m) {
+			t.Errorf("Encodable(%q) = false, want true", m)
+		}
+	}
+}
+
 // TestSSEBinGroundTruth checks the legacy packed/scalar binary family
 // byte for byte (no prefix / 66 / F2 / F3 variants).
 func TestSSEBinGroundTruth(t *testing.T) {

asm/evex.go

@@ -509,40 +509,43 @@ var evexBcastTable = map[string]evexBcastSpec{
 }
 
 // evexMoveSpec describes an EVEX move (load and store opcodes, like the VEX
-// move table).
+// move table).  vecOK and xmmOnly mirror the VEX twin's operand rules: a
+// scalar move (vecOK false, xmmOnly true) takes XMM↔memory operands only.
 type evexMoveSpec struct {
-	mapSel int
-	pp     int
-	load   byte // r/m → vector
-	store  byte // vector → r/m
-	w      int
-	n      [3]int
+	mapSel  int
+	pp      int
+	load    byte // r/m → vector
+	store   byte // vector → r/m
+	w       int
+	n       [3]int
+	vecOK   bool // the non-memory operand may be a vector register
+	xmmOnly bool // wider than XMM registers are rejected
 }
 
 // evexMoveTable maps an upper-case EVEX move mnemonic to its encoding.
 var evexMoveTable = map[string]evexMoveSpec{
 	// EVEX.128/256/512.F3.0F.W0, unaligned integer move.
-	"VMOVDQU32": {1, 2, 0x6F, 0x7F, 0, [3]int{16, 32, 64}},
+	"VMOVDQU32": {1, 2, 0x6F, 0x7F, 0, [3]int{16, 32, 64}, true, false},
 	// EVEX.128/256/512.F3.0F.W1, unaligned qword move.
-	"VMOVDQU64": {1, 2, 0x6F, 0x7F, 1, [3]int{16, 32, 64}},
+	"VMOVDQU64": {1, 2, 0x6F, 0x7F, 1, [3]int{16, 32, 64}, true, false},
 	// EVEX.128/256/512.F2.0F.W0, unaligned byte move (byte/word moves use the
 	// F2 prefix, dword/qword moves F3; the element size only changes the tuple
 	// semantics).
-	"VMOVDQU8": {1, 3, 0x6F, 0x7F, 0, [3]int{16, 32, 64}},
+	"VMOVDQU8": {1, 3, 0x6F, 0x7F, 0, [3]int{16, 32, 64}, true, false},
 	// EVEX.128/256/512.F2.0F.W1, unaligned word move (shares the qword
 	// encoding).
-	"VMOVDQU16": {1, 3, 0x6F, 0x7F, 1, [3]int{16, 32, 64}},
+	"VMOVDQU16": {1, 3, 0x6F, 0x7F, 1, [3]int{16, 32, 64}, true, false},
 	// EVEX.128/256/512.66.0F.W1, unaligned packed double move.
-	"VMOVUPD": {1, 1, 0x10, 0x11, 1, [3]int{16, 32, 64}},
+	"VMOVUPD": {1, 1, 0x10, 0x11, 1, [3]int{16, 32, 64}, true, false},
 	// EVEX.128/256/512, aligned packed moves.
-	"VMOVAPS": {1, 0, 0x28, 0x29, 0, [3]int{16, 32, 64}},
-	"VMOVAPD": {1, 1, 0x28, 0x29, 1, [3]int{16, 32, 64}},
+	"VMOVAPS": {1, 0, 0x28, 0x29, 0, [3]int{16, 32, 64}, true, false},
+	"VMOVAPD": {1, 1, 0x28, 0x29, 1, [3]int{16, 32, 64}, true, false},
 	// EVEX.128/256/512.66.0F, aligned integer moves.
-	"VMOVDQA32": {1, 1, 0x6F, 0x7F, 0, [3]int{16, 32, 64}},
-	"VMOVDQA64": {1, 1, 0x6F, 0x7F, 1, [3]int{16, 32, 64}},
+	"VMOVDQA32": {1, 1, 0x6F, 0x7F, 0, [3]int{16, 32, 64}, true, false},
+	"VMOVDQA64": {1, 1, 0x6F, 0x7F, 1, [3]int{16, 32, 64}, true, false},
 	// EVEX.128.F3.0F.W0, scalar single move, memory operands (the
 	// three-operand register form is not supported).
-	"VMOVSS": {1, 2, 0x10, 0x11, 0, [3]int{4, 4, 4}},
+	"VMOVSS": {1, 2, 0x10, 0x11, 0, [3]int{4, 4, 4}, false, true},
 }
 
 // isEvex reports whether the mnemonic has an EVEX encoding we handle.
@@ -1022,6 +1025,12 @@ func (e *enc) encodeEvexMove(mnem string, ms evexMoveSpec, ops []Operand, mask i
 	var rm Operand
 	switch {
 	case srcIsVec && dstIsVec:
+		// A store-form reg-reg move, the layout the Go assembler uses; a
+		// scalar move has no two-register form at all (the register form
+		// takes three operands), matching the VEX twin's vecOK rule.
+		if !ms.vecOK {
+			return fmt.Errorf("%s does not take two vector registers", mnem)
+		}
 		reg, rm = srcReg, dst
 	case srcIsVec:
 		if !memOperand(dst) {
@@ -1037,6 +1046,12 @@ func (e *enc) encodeEvexMove(mnem string, ms evexMoveSpec, ops []Operand, mask i
 	default:
 		return fmt.Errorf("%s needs a vector register operand", mnem)
 	}
+	// The scalar move is 128-bit only, so the register the length follows
+	// must be an XMM (the VEX twin's xmmOnly rule; EVEX also reaches ZMM,
+	// hence the inequality rather than a YMM test).
+	if ms.xmmOnly && reg.size != 16 {
+		return fmt.Errorf("%s operates on XMM registers only", mnem)
+	}
 	spec := evexSpec{mapSel: ms.mapSel, opcode: op, w: ms.w, pp: ms.pp, opdigit: -1, n: ms.n}
 	return e.emitEvexFields(spec, reg.vecLenBit(), reg.idx, -1, rm, mask, sfx)
 }
@@ -1171,9 +1186,6 @@ func (e *enc) emitEvexFields(spec evexSpec, ll, regIdx, vvvvIdx int, rm Operand,
 		if r.idx&16 != 0 {
 			xBar = 0
 		}
-		if r.idx&16 != 0 {
-			xBar = 0
-		}
 	case Mem:
 		var err error
 		modrm, sib, disp, xBar, bBar, err = memComponentsEvex(regIdx&7, r, spec.n[ll])
@@ -1232,6 +1244,11 @@ func (e *enc) emitEvexFields(spec evexSpec, ll, regIdx, vvvvIdx int, rm Operand,
 func memComponentsEvex(regField int, m Mem, n int) (modrm, sib int, disp []byte, xBar, bBar int, err error) {
 	sib = -1
 	xBar, bBar = 1, 1 // inverted bits: 1 = no extension
+	// The disp32 fallback bounds the displacement by int32, and the
+	// compressed disp8 form reaches at most ±127×64, well inside it.
+	if m.Disp < -(1<<31) || m.Disp > (1<<31)-1 {
+		return 0, -1, nil, 0, 0, fmt.Errorf("displacement %d does not fit in 32 bits", m.Disp)
+	}
 	if !m.HasBase && !m.HasIndex {
 		return regField<<3 | 0x05, -1, le32(m.Disp), 1, 1, nil // RIP-relative
 	}

asm/evex_test.go

@@ -675,6 +675,15 @@ func TestEvexErrors(t *testing.T) {
 		{"align arity", "VALIGND", []Operand{Imm(1), vreg(t, "Z0"), vreg(t, "Z1")}},
 		// VEX-only mnemonics reject registers only EVEX can encode.
 		{"VMOVMSKPS X16", "VMOVMSKPS", []Operand{vreg(t, "X16"), AX}},
+		// The scalar EVEX move matches its VEX twin and the Go assembler:
+		// XMM↔memory only, never reg-reg and never a wider register (the
+		// toolchain rejects every one of these shapes).
+		{"VMOVSS X1,X2", "VMOVSS", []Operand{vreg(t, "X1"), vreg(t, "X2")}},
+		{"VMOVSS X16,X2", "VMOVSS", []Operand{vreg(t, "X16"), vreg(t, "X2")}},
+		{"VMOVSS Y1,(AX)", "VMOVSS", []Operand{vreg(t, "Y1"), Ptr(AX, 0, 4)}},
+		{"VMOVSS Z1,Z2", "VMOVSS", []Operand{vreg(t, "Z1"), vreg(t, "Z2")}},
+		{"VMOVSS Z1,(AX)", "VMOVSS", []Operand{vreg(t, "Z1"), Ptr(AX, 0, 4)}},
+		{"VMOVSS (AX),Z2", "VMOVSS", []Operand{Ptr(AX, 0, 4), vreg(t, "Z2")}},
 	}
 	for _, c := range cases {
 		if _, err := Encode(c.mnem, c.ops...); err == nil {

asm/goobj.go

@@ -68,11 +68,12 @@ const (
 	kindSDWARFLINES = 20
 )
 
-// Symbol flags (cmd/internal/goobj).
+// Symbol flags (cmd/internal/goobj).  The linkname flag is set only for
+// //go:linkname symbols (and main.main); ordinary assembly symbols carry
+// none, matching cmd/asm's output.
 const (
 	symFlagDupok   = 0x01
 	symFlagNoSplit = 0x10
-	symFlag2Link   = 0x10 // asm objects flag every named symbol as linkname
 	symABIStatic   = 0xffff
 )
 
@@ -287,7 +288,7 @@ func (img *Image) emitGOObject(pkgPath, srcPath string, pre []byte, minLC int, r
 			}
 		}
 		nps = append(nps, npSym{
-			sym:  goSym{name: name, abi: abi, typ: kindSTEXT, flag: flag, flag2: symFlag2Link, size: uint32(fn.Size)},
+			sym:  goSym{name: name, abi: abi, typ: kindSTEXT, flag: flag, size: uint32(fn.Size)},
 			data: code,
 		})
 	}
@@ -317,7 +318,7 @@ func (img *Image) emitGOObject(pkgPath, srcPath string, pre []byte, minLC int, r
 			abi = symABIStatic
 		}
 		defIdx[d.Name] = len(defs)
-		defs = append(defs, goSym{name: name, abi: abi, typ: typ, flag: flag, flag2: symFlag2Link, size: uint32(d.Size)})
+		defs = append(defs, goSym{name: name, abi: abi, typ: typ, flag: flag, size: uint32(d.Size)})
 		defData = append(defData, img.Data[d.Offset:d.Offset+d.Size])
 	}
 	fnFiIdx := make([]int, len(img.Funcs))

asm/goobj_resolve.go

@@ -40,8 +40,11 @@ func exportPath(importPath string) (string, error) {
 //
 // refs maps package import paths to the symbol names referenced from that
 // package.  The returned pkgIdx maps each import path to its position in
-// the blkPkgIdx table (0-based), and symIdx gives each symbol's index within
-// its package.
+// the blkPkgIdx table, which reserves index 0 for the dummy invalid
+// package (cmd/internal/obj/sym.go: "0 is invalid index"; the loader's
+// reader loop starts at 1), so package i sits at block index i+1 and its
+// relocations carry i+1.  symIdx gives each symbol's index within its
+// package.
 func resolveExternalGOOBJ(refs map[string][]string) (pkgIdx map[string]int, symIdx map[string]int, err error) {
 	pkgIdx = make(map[string]int, len(refs))
 	symIdx = make(map[string]int)
@@ -50,7 +53,9 @@ func resolveExternalGOOBJ(refs map[string][]string) (pkgIdx map[string]int, symI
 	packages := sortedPkgRefs(refs)
 
 	for i, pkg := range packages {
-		pkgIdx[pkg.path] = i
+		// Block index 0 is the dummy invalid package; the first real
+		// package starts at 1.
+		pkgIdx[pkg.path] = i + 1
 		exp, err := exportPath(pkg.path)
 		if err != nil {
 			return nil, nil, err
@@ -145,40 +150,65 @@ func parseArDecimal(b []byte) int {
 }
 
 // goobjFile is a parsed GOOBJ file: the string table and the symbol-definition
-// block.
+// blocks.  The hashed blocks are kept raw: their symbols carry no names, only
+// the loader needs their counts.
 type goobjFile struct {
-	strTab []byte // string table, at headerSize + n
-	symdef []byte // blkSymdef raw block
-	npdef  []byte // blkNonpkgdef raw block
+	strTab   []byte // string table, at headerSize + n
+	symdef   []byte // blkSymdef raw block
+	hashed64 []byte // blkHashed64def raw block
+	hashed   []byte // blkHasheddef raw block
+	npdef    []byte // blkNonpkgdef raw block
 }
 
-// symbols returns all symbol names in definition order by scanning the
-// symdef and nonpkgdef blocks and resolving each name through the string
-// table.  Package definitions (blkSymdef) use fully-qualified names like
-// "runtime.morestack"; non-package definitions (blkNonpkgdef) use bare
-// names like "morestack".  This combined list matches the index the
-// linker expects for cross-package references.
+// loaderIndexBase returns the index the first nonpkgdef symbol occupies in the
+// loader's per-object symbol array.  cmd/link lays the definition blocks out as
+// symdef, hashed64def, hasheddef, nonpkgdef, nonpkgref (loader.go: preloadSyms
+// fills r.syms in exactly that order, and resolve() indexes PkgIdxNone and
+// cross-package SymIdx into it), so a symbol found in blkNonpkgdef carries the
+// three leading blocks' symbol counts as its base.
+func (f *goobjFile) loaderIndexBase() int {
+	return len(f.symdef)/recSymSize + len(f.hashed64)/recSymSize + len(f.hashed)/recSymSize
+}
+
+// symbols returns the names of the symdef and nonpkgdef blocks in
+// definition order.  Package definitions (blkSymdef) use fully-qualified
+// names like "runtime.morestack"; non-package definitions (blkNonpkgdef)
+// use bare names like "morestack".  For lookups by index prefer
+// findSymbol: it adds the hashed blocks' count the loader's array
+// interleaves between the two.
 func (f *goobjFile) symbols() []string {
 	return append(f.defNames(), f.npdefNames()...)
 }
 
-// findSymbol returns the index of a symbol within the combined symbol list,
-// or -1 if not found.  It first tries the fully-qualified name (pkg.name),
-// then the bare name.
+// findSymbol returns the index of a symbol within the loader's per-object
+// symbol array, or -1 if not found.  It first tries the fully-qualified
+// name (pkg.name), then the bare name (assembly objects store dotless
+// names, e.g. runtime's "gogo", for symbols other packages reach through
+// a linkname).
 func (f *goobjFile) findSymbol(pkg, name string) int {
+	base := f.loaderIndexBase()
 	qualified := pkg + "." + name
-	syms := f.symbols()
-	for i, s := range syms {
+	for i, s := range f.defNames() {
 		if s == qualified {
 			return i
 		}
 	}
-	// Try bare name (for non-package definitions).
-	for i, s := range syms {
+	for i, s := range f.npdefNames() {
+		if s == qualified {
+			return base + i
+		}
+	}
+	// Try bare name (for dotless assembly definitions).
+	for i, s := range f.defNames() {
 		if s == name {
 			return i
 		}
 	}
+	for i, s := range f.npdefNames() {
+		if s == name {
+			return base + i
+		}
+	}
 	return -1
 }
 
@@ -192,12 +222,16 @@ func (f *goobjFile) npdefNames() []string {
 	return f.readSymNames(f.npdef)
 }
 
+// recSymSize is the size of one Sym record in the definition blocks
+// (goobj.SymSize: stringRefSize + 2 + 1 + 1 + 1 + 4 + 4).
+const recSymSize = 21
+
 // readSymNames reads symbol names from a symdef/nonpkgdef block.  Each record
 // is 21 bytes: nameLen (u32), nameOff (u32), abi (u16), typ, flag, flag2,
 // size (u32), align (u32).  nameOff is an absolute offset into the string
 // table.
 func (f *goobjFile) readSymNames(block []byte) []string {
-	const recSize = 21
+	const recSize = recSymSize
 	if len(block) < recSize {
 		return nil
 	}
@@ -247,16 +281,18 @@ func parseGOOBJ(data []byte) (*goobjFile, error) {
 	//   [16:20] flags
 	//   [20:96] 19 × uint32 offsets
 	var offs [blkEnd + 1]uint32
-	for i := 0; i <= blkEnd; i++ {
+	for i := range blkEnd + 1 {
 		offs[i] = binary.LittleEndian.Uint32(payload[20+4*i:])
 	}
 	// The string table lives at headerSize.
 	strTabStart := uint32(goobjHeaderSize)
 
 	f := &goobjFile{
-		strTab: payload[strTabStart:offs[0]],
-		symdef: blockSlice(payload, offs, blkSymdef, blkSymdef+1),
-		npdef:  blockSlice(payload, offs, blkNonpkgdef, blkNonpkgdef+1),
+		strTab:   payload[strTabStart:offs[0]],
+		symdef:   blockSlice(payload, offs, blkSymdef, blkSymdef+1),
+		hashed64: blockSlice(payload, offs, blkHashed64def, blkHashed64def+1),
+		hashed:   blockSlice(payload, offs, blkHasheddef, blkHasheddef+1),
+		npdef:    blockSlice(payload, offs, blkNonpkgdef, blkNonpkgdef+1),
 	}
 	return f, nil
 }
@@ -306,22 +342,26 @@ func resolveExternalSymbols(externals []string) (pkgTable []string, pkgIdxMap ma
 		return nil, nil, nil, err
 	}
 
-	// Build the package table in pkgIdx order.
+	// Build the package table in pkgIdx order.  The indices are 1-based
+	// (0 is the dummy invalid package, written by the emitter itself), so
+	// the table without the dummy is indexed one below.
 	pkgTable = make([]string, len(pkgIdx1))
 	for pkg, idx := range pkgIdx1 {
-		pkgTable[idx] = pkg
+		pkgTable[idx-1] = pkg
 	}
 
 	return pkgTable, pkgIdx1, symIdx1, nil
 }
 
 // splitQualified splits a qualified Go symbol name (pkgpath·name) into its
-// package path and local name.  The separator is the middle dot (U+00B7).
-// If no separator is found, the symbol is assumed to be in the current
-// package (empty pkg).
+// package path and local name.  The separator is the middle dot (U+00B7),
+// whose UTF-8 encoding is two bytes, so the search must be string-based:
+// IndexByte would match only the second byte and leave the lead byte on
+// the package path.  If no separator is found, the symbol is assumed to be
+// in the current package (empty pkg).
 func splitQualified(full string) (pkg, name string) {
-	if idx := strings.IndexByte(full, '\u00b7'); idx >= 0 {
-		return full[:idx], full[idx+len("\u00b7"):]
+	if before, after, ok := strings.Cut(full, "\u00b7"); ok {
+		return before, after
 	}
 	if before, after, ok := strings.Cut(full, "."); ok {
 		return before, after

asm/goobj_resolve_test.go

@@ -56,8 +56,12 @@ func TestResolveExternalSymbols(t *testing.T) {
 	if err != nil {
 		t.Fatalf("resolveExternalGOOBJ: %v", err)
 	}
-	if len(pkgIdx) != 1 || pkgIdx["runtime"] != 0 {
-		t.Errorf("pkgIdx = %v, want runtime→0", pkgIdx)
+	if len(pkgIdx) != 1 || pkgIdx["runtime"] != 1 {
+		// Index 0 is the dummy invalid package in the blkPkgIdx table;
+		// the loader's reader loop starts at 1 (cmd/link/internal/
+		// loader/loader.go: "PkgIdx 0 is a dummy invalid package"), so
+		// the first real package must carry index 1.
+		t.Errorf("pkgIdx = %v, want runtime→1", pkgIdx)
 	}
 	if _, ok := symIdx["runtime·g0"]; !ok {
 		t.Errorf("symIdx missing runtime·g0, got %v", symIdx)

asm/goobj_test.go

@@ -117,7 +117,9 @@ DATA mask<>+8(SB)/8, $0x800f0e0d0c0b0a09
 	if len(defs) != 7 {
 		t.Fatalf("symdefs = %d, want 7", len(defs))
 	}
-	if defs[0].name != "mask" || defs[0].abi != 0xffff || defs[0].typ != kindSRODATA || defs[0].size != 16 || defs[0].flag2 != symFlag2Link {
+	// The linkname flag stays clear: the toolchain sets it only for
+	// //go:linkname symbols, and an ordinary static GLOBL is not one.
+	if defs[0].name != "mask" || defs[0].abi != 0xffff || defs[0].typ != kindSRODATA || defs[0].size != 16 || defs[0].flag2 != 0 {
 		t.Errorf("mask symbol = %+v", defs[0])
 	}
 	if defs[1].name != "" || defs[1].typ != kindSDATA || defs[1].size != 28 {
@@ -511,3 +513,188 @@ func fieldAfter(line, flag string) string {
 	}
 	return ""
 }
+
+// TestGOObjectExternalPackageLink is the cross-package end-to-end check: a
+// GOOBJ whose code references a real external package symbol (runtime's
+// morestack, a plain reference rather than the builtin noctxt form) must
+// carry a package index that points past the blkPkgIdx table's dummy entry
+// 0, and the object must link against the real runtime.  Pre-fix, the
+// relocations carried block index 0, which the loader never fills, so the
+// reference resolved against whatever object was loaded first and the link
+// failed.  The binary is not run: morestack returns to the call site's
+// stack check, which a hand-written caller has none of.
+func TestGOObjectExternalPackageLink(t *testing.T) {
+	goBin, err := exec.LookPath("go")
+	if err != nil {
+		t.Skip("no Go toolchain available")
+	}
+	dir := t.TempDir()
+
+	const asmSrc = `
+#include "textflag.h"
+
+TEXT ·fn(SB), NOSPLIT, $0-0
+	CALL ·helper(SB)
+	RET
+
+TEXT ·helper(SB), NOSPLIT, $0-0
+	RET
+`
+	const mainSrc = `package main
+
+func fn()
+func helper()
+
+func main() {
+	fn()
+	helper()
+}
+`
+	if err := os.WriteFile(filepath.Join(dir, "main_amd64.s"), []byte(asmSrc), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(filepath.Join(dir, "main.go"), []byte(mainSrc), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(filepath.Join(dir, "go.mod"), []byte("module extlink\n\ngo 1.27\n"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+
+	// Capture the build the toolchain performs and re-run only its link
+	// step with our object swapped into the package archive, mirroring
+	// TestGOObjectLinkAndRun.
+	build := exec.Command(goBin, "build", "-x", "-work", "-o", filepath.Join(dir, "prog"), ".")
+	build.Dir = dir
+	buildLog, err := build.CombinedOutput()
+	if err != nil {
+		t.Fatalf("baseline build: %v\n%s", err, buildLog)
+	}
+	var work, linkLine, asmObj, pkgArch string
+	for line := range strings.SplitSeq(string(buildLog), "\n") {
+		switch {
+		case strings.HasPrefix(line, "WORK="):
+			work = strings.TrimPrefix(line, "WORK=")
+		case strings.Contains(line, "/asm ") && strings.Contains(line, "main_amd64.s") && !strings.Contains(line, "-gensymabis"):
+			asmObj = fieldAfter(line, "-o")
+		case strings.Contains(line, "pack r") && strings.Contains(line, "_pkg_.a"):
+			pkgArch = strings.TrimSpace(strings.SplitN(line, "pack r", 2)[1])
+			pkgArch = strings.Fields(strings.SplitN(pkgArch, "#", 2)[0])[0]
+		case strings.Contains(line, "/link ") && strings.Contains(line, "-importcfg"):
+			linkLine = line
+		}
+	}
+	if work == "" || asmObj == "" || pkgArch == "" || linkLine == "" {
+		t.Skipf("could not parse build log (work=%q asmObj=%q)", work, asmObj)
+	}
+	defer os.RemoveAll(work)
+	asmObj = strings.ReplaceAll(asmObj, "$WORK", work)
+	pkgArch = strings.ReplaceAll(pkgArch, "$WORK", work)
+
+	// Assemble the source with gasm, then retarget fn's internal call at
+	// a real external package symbol: the reloc's qualified name drives
+	// the export-data resolution the way a source-level runtime·sym(SB)
+	// reference would.
+	f, errs := parser.Parse("main_amd64.s", asmSrc)
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFile(f)
+	if err != nil {
+		t.Fatalf("AssembleFile: %v", err)
+	}
+	fn := &img.Funcs[0]
+	for i := range fn.Relocs {
+		fn.Relocs[i].Name = "runtime\u00b7morestack"
+		fn.Relocs[i].External = true
+	}
+	img.Externals = []string{"runtime\u00b7morestack"}
+	obj, err := img.GOObject("main", "main_amd64.s")
+	if err != nil {
+		t.Fatalf("GOObject: %v", err)
+	}
+
+	// Structural check: the blkPkgIdx block reserves entry 0 for the
+	// dummy invalid package and places runtime at entry 1, and fn's call
+	// relocation carries PkgIdx 1.
+	v := openGoobj(t, obj)
+	pkgBlk := v.blk(blkPkgIdx)
+	if len(pkgBlk) != 2*8 {
+		t.Fatalf("blkPkgIdx = %d bytes, want two entries", len(pkgBlk))
+	}
+	le := binary.LittleEndian
+	strEntry := func(i int) string {
+		e := pkgBlk[i*8 : (i+1)*8]
+		return v.str(le.Uint32(e[4:]), le.Uint32(e[0:]))
+	}
+	if s := strEntry(0); s != "" {
+		t.Errorf("blkPkgIdx[0] = %q, want the dummy empty package", s)
+	}
+	if s := strEntry(1); s != "runtime" {
+		t.Errorf("blkPkgIdx[1] = %q, want runtime", s)
+	}
+	relocs := v.blk(blkReloc)
+	// fn is the last non-package symbol (two functions, four pc tables
+	// each); its one reloc is the final record.
+	fnRec := relocs[len(relocs)-23:]
+	if pIdx := le.Uint32(fnRec[15:]); pIdx != 1 {
+		t.Errorf("external reloc PkgIdx = %d, want 1 (runtime)", pIdx)
+	}
+
+	// Swap the object into the package archive and link with cmd/link;
+	// the link line consumes the archive, not the loose object file.
+	membersDir := filepath.Join(dir, "members")
+	if err := os.MkdirAll(membersDir, 0o755); err != nil {
+		t.Fatal(err)
+	}
+	extract := exec.Command(goBin, "tool", "pack", "x", pkgArch)
+	extract.Dir = membersDir
+	if out, err := extract.CombinedOutput(); err != nil {
+		t.Fatalf("pack x: %v\n%s", err, out)
+	}
+	member := filepath.Join(membersDir, filepath.Base(asmObj))
+	if err := os.Chmod(member, 0o644); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(member, obj, 0o644); err != nil {
+		t.Fatal(err)
+	}
+	listCmd := exec.Command(goBin, "tool", "pack", "t", pkgArch)
+	listOut, err := listCmd.CombinedOutput()
+	if err != nil {
+		t.Fatalf("pack t: %v\n%s", err, listOut)
+	}
+	newArch := filepath.Join(dir, "pkg.a")
+	args := []string{"tool", "pack", "c", newArch}
+	seen := map[string]bool{}
+	for m := range strings.FieldsSeq(string(listOut)) {
+		if seen[m] {
+			continue
+		}
+		seen[m] = true
+		if err := os.Chmod(filepath.Join(membersDir, m), 0o644); err != nil {
+			t.Fatal(err)
+		}
+		args = append(args, filepath.Join(membersDir, m))
+	}
+	pack := exec.Command(goBin, args...)
+	pack.Dir = membersDir
+	if out, err := pack.CombinedOutput(); err != nil {
+		t.Fatalf("pack c: %v\n%s", err, out)
+	}
+	linkLine = strings.ReplaceAll(linkLine, "$WORK", work)
+	linkLine = strings.ReplaceAll(linkLine, pkgArch, newArch)
+	linkLine = strings.ReplaceAll(linkLine, filepath.Join(work, "b001", "exe", "a.out"), filepath.Join(dir, "prog2"))
+	linkCmd := exec.Command("sh", "-c", "cd "+dir+" && "+linkLine)
+	if out, err := linkCmd.CombinedOutput(); err != nil {
+		t.Fatalf("re-link with gasm object: %v\n%s", err, out)
+	}
+
+	// The call must have resolved to the real runtime symbol.
+	dump, err := exec.Command(goBin, "tool", "objdump", "-s", "main.fn", filepath.Join(dir, "prog2")).CombinedOutput()
+	if err != nil {
+		t.Fatalf("objdump main.fn: %v\n%s", err, dump)
+	}
+	if !bytes.Contains(dump, []byte("runtime.morestack")) {
+		t.Errorf("main.fn does not call runtime.morestack:\n%s", dump)
+	}
+}

asm/goobjarm64.go

@@ -18,19 +18,40 @@ import (
 // reloc/aux/data index arrays, with the arm64 preamble, the MinLC of 4
 // for the pc-value deltas, and the arm64 relocation types for the ADRP
 // pairs and BL calls.
+//
+// The toolchain records one relocation per ADRP pair: a single R_ADDRARM64
+// or R_ARM64_PCREL_LDST64 of Siz 8 at the ADRP word, from which the linker
+// patches both instructions of the pair (cmd/internal/obj/arm64/asm7.go,
+// the ADRP cases: one AddRel with Off at the pair's pc and Siz 8).  gasm's
+// assembler records the ADRP+ADD form as two word relocs, so the second
+// word's twin is dropped here before emission.
 func (img *Image) GOObjectAARCH64(pkgPath, srcPath string) ([]byte, error) {
 	pre, err := toolchainObjectPreambleAARCH64()
 	if err != nil {
 		return nil, err
 	}
-	return img.emitGOObject(pkgPath, srcPath, pre, 4, func(r Reloc) (uint16, uint8) {
+	coalesced := *img
+	coalesced.Funcs = append([]FuncLayout(nil), img.Funcs...)
+	for i := range coalesced.Funcs {
+		rs := coalesced.Funcs[i].Relocs
+		var keep []Reloc
+		for j := 0; j < len(rs); j++ {
+			keep = append(keep, rs[j])
+			if rs[j].Kind == RelArm64Addr && j+1 < len(rs) &&
+				rs[j+1].Kind == RelArm64Addr && rs[j+1].Off == rs[j].Off+4 {
+				j++ // the ADD word's twin: the Siz-8 pair reloc covers it
+			}
+		}
+		coalesced.Funcs[i].Relocs = keep
+	}
+	return coalesced.emitGOObject(pkgPath, srcPath, pre, 4, func(r Reloc) (uint16, uint8) {
 		switch r.Kind {
 		case RelArm64Branch:
 			return relocArm64Branch, 4
 		case RelArm64LDST64:
-			return relocArm64LDST64, 4
+			return relocArm64LDST64, 8
 		default:
-			return relocArm64Addr, 4
+			return relocArm64Addr, 8
 		}
 	})
 }

asm/guard_test.go

@@ -6,6 +6,7 @@ package asm
 import (
 	"bytes"
 	"encoding/hex"
+	"strings"
 	"testing"
 
 	"sourcedock.dev/petrbalvin/gasm-devkit/ast"
@@ -27,6 +28,12 @@ func TestStackGuardBytes(t *testing.T) {
 			"644c8b3425000000004c8da42478ffffff4d3b66107614554889e54881ec000100004881c4000100005dc3e800000000ebce"},
 		{"leafbig", "TEXT \u00b7leafbig(SB), $8192-0\n\tRET\n",
 			"644c8b3425000000004989e44981ec881f0000721a4d3b66107614554889e54881ec002000004881c4002000005dc3e800000000ebca"},
+		// Class 2 with a body long enough that the underflow JB relaxes to
+		// rel32: its displacement must span the real 6-byte JB, else the
+		// branch lands 4 bytes past the morestack block, inside the CALL
+		// displacement field.
+		{"leafbiglong", "TEXT \u00b7leafbiglong(SB), $8192-0\n" + strings.Repeat("\tMOVQ AX, BX\n", 40) + "\tRET\n",
+			"644c8b3425000000004989e44981ec881f00000f82960000004d3b66100f868c000000554889e54881ec00200000" + strings.Repeat("4889c3", 40) + "4881c4002000005dc3e800000000e947ffffff"},
 		{"callsmall", "TEXT \u00b7callsmall(SB), $16-0\n\tCALL \u00b7other(SB)\n\tRET\nTEXT \u00b7other(SB), NOSPLIT, $0\n\tRET\n",
 			"644c8b342500000000493b66107613554889e54883ec10e8000000004883c4105dc3e800000000ebd7"},
 		{"nosplit", "TEXT \u00b7nosplit(SB), NOSPLIT, $16-0\n\tRET\n",
@@ -145,6 +152,45 @@ func TestStackGuardBytesARM64(t *testing.T) {
 	}
 }
 
+// TestStackGuardBranchTargetsARM64 checks the class-2 guard's branch
+// positions for a frame whose guard constant needs two MOV words: the
+// displacements must be computed from byte offsets (8+4*ml and 16+4*ml), so
+// both branches land on the morestack block rather than inside the body.
+// The frame size makes the toolchain switch its own prologue decomposition,
+// so the assertion is on the branch targets, not pinned bytes.
+func TestStackGuardBranchTargetsARM64(t *testing.T) {
+	f, errs := parser.Parse("g_arm64.s", "TEXT \u00b7f(SB), $65664-0\n\tCALL \u00b7other(SB)\n\tRET\nTEXT \u00b7other(SB), NOSPLIT, $0\n\tRET\n")
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFileARM64(f)
+	if err != nil {
+		t.Fatalf("assemble: %v", err)
+	}
+	fn := img.Funcs[0]
+	code := img.Code[fn.Offset : fn.Offset+fn.Size]
+	if len(code)%4 != 0 {
+		t.Fatalf("function size %d is not a word multiple", len(code))
+	}
+	// autosize = 65680, so the guard materialises 65552 = MOVZ+MOVK: ml = 2
+	// and the branches sit at bytes 16 and 24 of the guard prefix.
+	const morestackBlock = 12 // MOVD R30, R3; BL; B back
+	blockStart := len(code) - morestackBlock
+	check := func(name string, off int) {
+		t.Helper()
+		w := leWord(code[off:])
+		imm19 := int32(w>>5) & 0x7FFFF
+		if imm19&(1<<18) != 0 {
+			imm19 -= 1 << 19
+		}
+		if target := off + int(imm19)*4; target != blockStart {
+			t.Errorf("%s at byte %d targets byte %d, want the morestack block at %d", name, off, target, blockStart)
+		}
+	}
+	check("B.LO", 16)
+	check("B.LS", 24)
+}
+
 // The riscv64 stack-split guard, pinned from `go tool asm` (Go 1.27,
 // riscv64): the morestack call sits between the guard and the body, and the
 // guard branches forward over it.  Relocation fields are masked.

asm/instrs.go

@@ -173,7 +173,11 @@ func (e *enc) encodeMov(ops []Operand, size int) error {
 			if dstReg.needsREX(size) {
 				i.rexForced = true
 			}
-			i.imm = immediate(v, size, true)
+			imm, err := immediate(v, size, true)
+			if err != nil {
+				return err
+			}
+			i.imm = imm
 			return e.emit(i)
 		}
 		// MOV r/m, imm: 0xC6 (8-bit) / 0xC7 /0.
@@ -185,7 +189,11 @@ func (e *enc) encodeMov(ops []Operand, size int) error {
 		if err := setRMDigit(i, 0, dst, size); err != nil {
 			return err
 		}
-		i.imm = immediate(int64(src), size, false)
+		imm, err := immediate(int64(src), size, false)
+		if err != nil {
+			return err
+		}
+		i.imm = imm
 		return e.emit(i)
 	}
 	return fmt.Errorf("MOV: invalid operands")
@@ -297,11 +305,15 @@ func (e *enc) encodeALU(op struct {
 
 func (e *enc) encodeALUImm(digit int, dst Operand, imm int64, size int) error {
 	if size == 1 {
+		immBytes, err := immediate(imm, 1, false)
+		if err != nil {
+			return err
+		}
 		i := newInstr(1, []byte{0x80})
 		if err := setRMDigit(i, digit, dst, 1); err != nil {
 			return err
 		}
-		i.imm = []byte{byte(int8(imm))}
+		i.imm = immBytes
 		return e.emit(i)
 	}
 	if fits8(imm) {
@@ -319,7 +331,11 @@ func (e *enc) encodeALUImm(digit int, dst Operand, imm int64, size int) error {
 	if r, ok := dst.(Reg); ok && r.idx == 0 {
 		accOp := map[int]byte{0: 0x05, 1: 0x0D, 2: 0x15, 3: 0x1D, 4: 0x25, 5: 0x2D, 6: 0x35, 7: 0x3D}[digit]
 		i := newInstr(size, []byte{accOp})
-		i.imm = immediate(imm, size, false)
+		immBytes, err := immediate(imm, size, false)
+		if err != nil {
+			return err
+		}
+		i.imm = immBytes
 		return e.emit(i)
 	}
 	// 0x81 /digit, imm16/imm32.
@@ -327,7 +343,11 @@ func (e *enc) encodeALUImm(digit int, dst Operand, imm int64, size int) error {
 	if err := setRMDigit(i, digit, dst, size); err != nil {
 		return err
 	}
-	i.imm = immediate(imm, size, false)
+	immBytes, err := immediate(imm, size, false)
+	if err != nil {
+		return err
+	}
+	i.imm = immBytes
 	return e.emit(i)
 }
 
@@ -348,7 +368,11 @@ func (e *enc) encodeTest(ops []Operand, size int) error {
 				op = 0xA8
 			}
 			i := newInstr(size, []byte{op})
-			i.imm = immediate(int64(imm), size, false)
+			immBytes, err := immediate(int64(imm), size, false)
+			if err != nil {
+				return err
+			}
+			i.imm = immBytes
 			return e.emit(i)
 		}
 		op := byte(0xF7)
@@ -359,7 +383,11 @@ func (e *enc) encodeTest(ops []Operand, size int) error {
 		if err := setRMDigit(i, 0, dst, size); err != nil {
 			return err
 		}
-		i.imm = immediate(int64(imm), size, false)
+		immBytes, err := immediate(int64(imm), size, false)
+		if err != nil {
+			return err
+		}
+		i.imm = immBytes
 		return e.emit(i)
 	}
 	srcReg, ok := src.(Reg)
@@ -457,7 +485,13 @@ func (e *enc) encodeShift(digit int, ops []Operand, size int) error {
 		}
 		return e.emit(i)
 	}
-	// 0xC0 (8-bit) / 0xC1, imm8.
+	// 0xC0 (8-bit) / 0xC1, imm8.  The count is an unsigned byte: go tool asm
+	// rejects negative and ≥256 counts, and the hardware masks the count, so
+	// a silent truncation ($300 encoding 44) would shift by a different
+	// amount than the source states.
+	if imm < 0 || imm > 255 {
+		return fmt.Errorf("shift count $%d is out of the 0..255 range", int64(imm))
+	}
 	op := byte(0xC1)
 	if size == 1 {
 		op = 0xC0
@@ -466,7 +500,7 @@ func (e *enc) encodeShift(digit int, ops []Operand, size int) error {
 	if err := setRMDigit(i, digit, dst, size); err != nil {
 		return err
 	}
-	i.imm = []byte{byte(int8(imm))}
+	i.imm = []byte{byte(imm)}
 	return e.emit(i)
 }
 
@@ -508,7 +542,11 @@ func (e *enc) encodeImul(ops []Operand, size int) error {
 		if err := setRM(i, dstReg, ops[1], size); err != nil {
 			return err
 		}
-		i.imm = immediate(int64(imm), size, false)
+		immBytes, err := immediate(int64(imm), size, false)
+		if err != nil {
+			return err
+		}
+		i.imm = immBytes
 		return e.emit(i)
 	}
 	return fmt.Errorf("IMUL expects 2 or 3 operands, got %d", len(ops))
@@ -516,10 +554,21 @@ func (e *enc) encodeImul(ops []Operand, size int) error {
 
 // --- PUSH / POP -------------------------------------------------------------
 
-func (e *enc) encodePushPop(ops []Operand, push bool) error {
+func (e *enc) encodePushPop(ops []Operand, size int, push bool) error {
 	if len(ops) != 1 {
 		return fmt.Errorf("PUSH/POP expects 1 operand, got %d", len(ops))
 	}
+	// In 64-bit mode go tool asm knows the 64-bit push (the default, with or
+	// without the Q suffix) and the 16-bit W form with its 0x66 operand-size
+	// prefix, and rejects the B and L spellings outright ("illegal in 64-bit
+	// mode"); silently widening those would push a different width than the
+	// source states.
+	switch size {
+	case 0, 8, 2:
+	default:
+		return fmt.Errorf("PUSH/POP size suffix is illegal in 64-bit mode")
+	}
+	w16 := size == 2
 	switch op := ops[0].(type) {
 	case Reg:
 		base := byte(0x50) // PUSH r; POP is 0x58
@@ -527,7 +576,7 @@ func (e *enc) encodePushPop(ops []Operand, push bool) error {
 			base = 0x58
 		}
 		// PUSH/POP default to 64-bit in 64-bit mode; no REX.W needed.
-		i := &instr{opcode: []byte{base + byte(op.idx&7)}, modrm: -1, sib: -1}
+		i := &instr{opSize16: w16, opcode: []byte{base + byte(op.idx&7)}, modrm: -1, sib: -1}
 		i.rexB = op.idx >= 8
 		return e.emit(i)
 	case Mem:
@@ -537,7 +586,7 @@ func (e *enc) encodePushPop(ops []Operand, push bool) error {
 			opc = 0x8F // POP r/m: /0
 			digit = 0
 		}
-		i := &instr{opcode: []byte{opc}, modrm: -1, sib: -1}
+		i := &instr{opSize16: w16, opcode: []byte{opc}, modrm: -1, sib: -1}
 		if err := setRMDigit(i, digit, ops[0], 8); err != nil {
 			return err
 		}
@@ -547,10 +596,17 @@ func (e *enc) encodePushPop(ops []Operand, push bool) error {
 			return fmt.Errorf("POP does not take an immediate")
 		}
 		if fits8(int64(op)) {
-			i := &instr{opcode: []byte{0x6A}, modrm: -1, sib: -1, imm: []byte{byte(int8(op))}}
+			i := &instr{opSize16: w16, opcode: []byte{0x6A}, modrm: -1, sib: -1, imm: []byte{byte(int8(op))}}
 			return e.emit(i)
 		}
-		i := &instr{opSize16: false, opcode: []byte{0x68}, modrm: -1, sib: -1, imm: le32(int64(op))}
+		// PUSH imm32, sign-extended to 64 bits; go tool asm bounds the
+		// immediate by the same signed/unsigned 32-bit span as every other
+		// scalar immediate.
+		immBytes, err := immediate(int64(op), 8, false)
+		if err != nil {
+			return err
+		}
+		i := &instr{opSize16: w16, opcode: []byte{0x68}, modrm: -1, sib: -1, imm: immBytes}
 		return e.emit(i)
 	}
 	return fmt.Errorf("PUSH/POP: invalid operand")
@@ -639,19 +695,28 @@ func (e *enc) encodeJcc(cc int, ops []Operand) error {
 // immediate encodes an immediate of the given operand size.  full64 selects the
 // 64-bit immediate form (only valid for MOV r64, imm64); otherwise a 32-bit
 // sign-extended immediate is used for 64-bit operands.
-func immediate(v int64, size int, full64 bool) []byte {
+//
+// The span mirrors go tool asm: every scalar immediate must fit a signed or
+// unsigned 32-bit word, and the narrower fields then take the low bits
+// silently (ADDB $256, AL encodes imm8 0, MOVW $65536, AX imm16 0).  Only the
+// imm64 form may exceed the span; anything wider elsewhere is an error rather
+// than a truncation the source never asked for.
+func immediate(v int64, size int, full64 bool) ([]byte, error) {
+	if !(size == 8 && full64) && (v < -(1<<31) || v > (1<<32)-1) {
+		return nil, fmt.Errorf("immediate $%d does not fit in 32 bits", v)
+	}
 	switch size {
 	case 1:
-		return []byte{byte(int8(v))}
+		return []byte{byte(int8(v))}, nil
 	case 2:
-		return le16(v)
+		return le16(v), nil
 	case 4:
-		return le32(v)
+		return le32(v), nil
 	default: // 8
 		if full64 {
-			return le64(v)
+			return le64(v), nil
 		}
-		return le32(v) // sign-extended imm32
+		return le32(v), nil // sign-extended imm32
 	}
 }
 
@@ -773,15 +838,24 @@ func (e *enc) encodeBswap(ops []Operand, size int) error {
 // width.  The source is narrower than the destination, so the plain size-suffix
 // convention does not apply to these names.
 var movExtendOp = map[string]struct {
-	op    []byte
-	dst64 bool
+	op      []byte
+	dstSize int
 }{
-	"MOVBLZX": {[]byte{0x0F, 0xB6}, false}, // byte → long, zero-extend
-	"MOVBQZX": {[]byte{0x0F, 0xB6}, true},  // byte → quad, zero-extend
-	"MOVWLZX": {[]byte{0x0F, 0xB7}, false}, // word → long, zero-extend
-	"MOVWQZX": {[]byte{0x0F, 0xB7}, true},  // word → quad, zero-extend
-	"MOVWLSX": {[]byte{0x0F, 0xBF}, false}, // word → long, sign-extend
-	"MOVLQSX": {[]byte{0x63}, true},        // long → quad, sign-extend (MOVSXD)
+	"MOVBLZX": {[]byte{0x0F, 0xB6}, 4}, // byte → long, zero-extend
+	"MOVBQZX": {[]byte{0x0F, 0xB6}, 8}, // byte → quad, zero-extend
+	"MOVWLZX": {[]byte{0x0F, 0xB7}, 4}, // word → long, zero-extend
+	"MOVWQZX": {[]byte{0x0F, 0xB7}, 8}, // word → quad, zero-extend
+	"MOVWLSX": {[]byte{0x0F, 0xBF}, 4}, // word → long, sign-extend
+	"MOVLQSX": {[]byte{0x63}, 8},       // long → quad, sign-extend (MOVSXD)
+	"MOVBWZX": {[]byte{0x0F, 0xB6}, 2}, // byte → word, zero-extend
+	"MOVBWSX": {[]byte{0x0F, 0xBE}, 2}, // byte → word, sign-extend
+	"MOVBLSX": {[]byte{0x0F, 0xBE}, 4}, // byte → long, sign-extend
+	"MOVBQSX": {[]byte{0x0F, 0xBE}, 8}, // byte → quad, sign-extend
+	"MOVWQSX": {[]byte{0x0F, 0xBF}, 8}, // word → quad, sign-extend
+	// A long → quad zero-extend is a plain 32-bit move: every 32-bit
+	// operation zero-extends its result into the full register, so the
+	// toolchain lowers MOVLQZX to the plain MOVL encoding.
+	"MOVLQZX": {[]byte{0x8B}, 4},
 }
 
 // encodeMovExtend encodes a mixed-width extending move: reg = dst (the wider
@@ -795,12 +869,30 @@ func (e *enc) encodeMovExtend(base string, ops []Operand) error {
 	if !ok {
 		return fmt.Errorf("%s destination must be a register", base)
 	}
-	size := 4
-	if spec.dst64 {
-		size = 8
+	i := newInstr(spec.dstSize, spec.op)
+	if err := setRM(i, dstReg, ops[0], spec.dstSize); err != nil {
+		return err
 	}
-	i := newInstr(size, spec.op)
-	if err := setRM(i, dstReg, ops[0], size); err != nil {
+	return e.emit(i)
+}
+
+// encodePmovmskb encodes PMOVMSKB, the legacy SSE2 byte mask extract: the
+// XMM source's sign bytes pack into a GP destination, 66 0F D7 /r.
+func (e *enc) encodePmovmskb(base string, ops []Operand) error {
+	if len(ops) != 2 {
+		return fmt.Errorf("%s expects 2 operands, got %d", base, len(ops))
+	}
+	srcReg, srcVec := vecReg(ops[0])
+	if !srcVec {
+		return fmt.Errorf("%s source must be an XMM register", base)
+	}
+	dstReg, ok := ops[1].(Reg)
+	if !ok {
+		return fmt.Errorf("%s destination must be a register", base)
+	}
+	i := newInstr(4, []byte{0x0F, 0xD7})
+	i.prefix = 0x66
+	if err := setRM(i, dstReg, srcReg, 4); err != nil {
 		return err
 	}
 	return e.emit(i)

asm/link.go

@@ -25,6 +25,10 @@ type Image struct {
 	Symbols   map[string]int // static symbol → byte offset within the image
 	DataSyms  []DataSymbol   // GLOBL symbols, in layout order
 	Externals []string       // referenced but undefined symbols, sorted
+	// SourcePath is the assembled file's path, recorded in the DWARF
+	// sections in place of a placeholder name.  Empty when the image was
+	// not built from a named file.
+	SourcePath string
 }
 
 // FuncLayout describes one assembled function within an Image.
@@ -81,12 +85,9 @@ func (fl *FuncLayout) LineAt(offset int) int {
 	return 0
 }
 
-// RelocKind Reloc is one static-symbol reference within a function body: the disp32
-// field at Off (function-relative) must reach the symbol plus Addend,
-// measured from After, the address just past the instruction.  An External
-// relocation names a symbol no GLOBL in the file defines; the object-file
-// emitters carry it into the output's relocation table.
-// RelocKind discriminates the type of relocation needed.
+// RelocKind discriminates the relocation a static-symbol reference needs;
+// the encoders record one per SB reference, and the object-file emitters map
+// it to their format's relocation type.
 type RelocKind int
 
 const (
@@ -96,7 +97,6 @@ const (
 	RelRISCVPCRELIType                  // R_RISCV_PCREL_ITYPE (AUIPC + I-type pair)
 	RelRISCVPCRELSType                  // R_RISCV_PCREL_STYPE (AUIPC + S-type pair)
 	RelRISCVJal                         // R_RISCV_JAL (J-type call)
-	RelPCRelAbs                         // 32-bit absolute (R_RISCV_32)
 	RelLoong64AddrHi                    // R_LOONG64_ADDR_HI (pcalau12i)
 	RelLoong64AddrLo                    // R_LOONG64_ADDR_LO (addi.d/ld/st)
 	RelArm64Addr                        // R_ADDRARM64 (ADRP + ADD pair)
@@ -106,6 +106,13 @@ const (
 )
 
 type Reloc struct {
+	// Off is the function-relative offset of the field the linker patches
+	// and After the address just past the instruction, the base the
+	// assembler measures PC-relative displacements from.  Name plus
+	// Addend select the target: the symbol plus the byte offset.  An
+	// External relocation names a symbol no GLOBL in the file defines;
+	// the object-file emitters carry it into the output's relocation
+	// table.
 	Off      int
 	After    int
 	Name     string
@@ -150,7 +157,7 @@ func AssembleFile(f *ast.File) (*Image, error) {
 	}
 	link := &linkInfo{symbols: known, allowExternal: true}
 
-	img := &Image{Symbols: map[string]int{}}
+	img := &Image{Symbols: map[string]int{}, SourcePath: f.Path}
 	textOff := map[string]int{}
 	type asmFunc struct {
 		name    string
@@ -267,7 +274,7 @@ func AssembleFileRISCV(f *ast.File) (*Image, error) {
 		return nil, err
 	}
 
-	img := &Image{Symbols: map[string]int{}}
+	img := &Image{Symbols: map[string]int{}, SourcePath: f.Path}
 	for _, d := range f.Decls {
 		t, ok := d.(*ast.Text)
 		if !ok {
@@ -339,7 +346,7 @@ func AssembleFileLOONG64(f *ast.File) (*Image, error) {
 		return nil, err
 	}
 
-	img := &Image{Symbols: map[string]int{}}
+	img := &Image{Symbols: map[string]int{}, SourcePath: f.Path}
 	for _, d := range f.Decls {
 		t, ok := d.(*ast.Text)
 		if !ok {

asm/loong64_assemble.go

@@ -442,6 +442,15 @@ func encodeLOONG64Instr(instr *ast.Instr, pc int, offsets map[string]int, fi loo
 		if rj < 0 || rd < 0 {
 			return nil, fmt.Errorf("invalid register operand")
 		}
+		// The toolchain validates the bit numbers ("illegal bit number"):
+		// 0..31 for the .w forms, 0..63 for the .d forms, lsb <= msb.
+		b := 64
+		if strings.HasSuffix(mnem, "W") {
+			b = 32
+		}
+		if msb < 0 || msb >= b || lsb < 0 || lsb >= b || lsb > msb {
+			return nil, fmt.Errorf("%s: illegal bit number (msb %d, lsb %d)", mnem, msb, lsb)
+		}
 		return l64wordLE(l64irir(enc.op, msb, rj, lsb, rd)), nil
 
 	case l64Firrr:
@@ -618,6 +627,15 @@ func encodeLOONG64Branch16(mnem string, op uint32, ops []*ast.Operand, pc int, o
 		if rj < 0 {
 			return nil, fmt.Errorf("invalid register operand")
 		}
+		if mnem == "BLTU" || mnem == "BGEU" {
+			// The unsigned compares have no single-register pseudo: the
+			// toolchain keeps the register-register form with rd = R0
+			// (bltu rj, r0 is never taken), not a sometimes-taken beqz.
+			if (v<<16)>>16 != v {
+				return nil, fmt.Errorf("branch to %q too far (16-bit range)", target)
+			}
+			return l64wordLE(l64irr16(op, v, rj, 0)), nil
+		}
 		if (v<<11)>>11 != v {
 			return nil, fmt.Errorf("branch to %q too far (21-bit range)", target)
 		}
@@ -857,9 +875,16 @@ func encodeLOONG64Mov(instr *ast.Instr, mnem string, fi loong64FrameInfo, relocs
 		if rd < 0 {
 			return nil, fmt.Errorf("%s $imm: invalid destination register", mnem)
 		}
-		// MOVF/MOVD $imm, Fd → materialise in R30, then movgr2fr.{w,d}.
-		if (mnem == "MOVF" || mnem == "MOVD") && loong64RegClass(operandRegName(dst)) == l64ClsFP {
-			return encodeLOONG64ImmToFp(rd, l64Imm64(src), mnem), nil
+		// MOVW $imm, Fd is the only immediate-to-F form the toolchain's optab
+		// accepts (AMOVW's C_12CON against C_FREG): it materialises the
+		// constant in R30 and moves it across with movgr2fr.w.  MOVV/MOVF/
+		// MOVD are illegal combinations there, and are diagnosed here rather
+		// than silently written into the GPR of the register's number.
+		if loong64RegClass(operandRegName(dst)) == l64ClsFP {
+			if mnem != "MOVW" {
+				return nil, fmt.Errorf("%s $imm: illegal combination with an F register destination (only MOVW $c, Fd is supported)", mnem)
+			}
+			return encodeLOONG64ImmToFp(rd, l64Imm64(src))
 		}
 		return encodeLOONG64LoadImm(rd, l64Imm64(src), mnem), nil
 	}
@@ -940,8 +965,8 @@ func loong64MovSize(mnem string, ops []*ast.Operand, fi loong64FrameInfo) int {
 		if src.Imm.Sym != nil && src.Imm.Sym.Pseudo == "SB" {
 			return 8 // pcalau12i + addi.d
 		}
-		if (mnem == "MOVF" || mnem == "MOVD") && loong64RegClass(operandRegName(dst)) == l64ClsFP {
-			return 8 // addi/ori r30 + movgr2fr
+		if loong64RegClass(operandRegName(dst)) == l64ClsFP {
+			return 8 // ori/addi.w r30 + movgr2fr.w (an encode-time diagnostic when invalid)
 		}
 		v := l64Imm64(src)
 		if v == 0 {
@@ -982,22 +1007,24 @@ func loong64MovSize(mnem string, ops []*ast.Operand, fi loong64FrameInfo) int {
 	}
 }
 
-// encodeLOONG64ImmToFp materialises a 12-bit immediate in R30 and moves it to
-// an F register (the toolchain's case 34: movgr2fr.w/movgr2fr.d).
-func encodeLOONG64ImmToFp(fd int, v int64, mnem string) []byte {
-	// ori for positive constants, addi.d for zero/negative.
-	op := uint32(0x00b << 22)
-	if v > 0 {
-		op = 0x00e << 22
+// encodeLOONG64ImmToFp materialises a 12-bit immediate in R30 and moves it
+// to an F register, the toolchain's expansion of MOVW $c, Fd: ori (which
+// zero-extends) for the positive span, addi.w for zero and the negative
+// span, then movgr2fr.w.  The toolchain's optab accepts no wider constant on
+// this path (it never materialises one fully first), so values outside
+// [-2048, 4095] are diagnosed rather than masked into si12.
+func encodeLOONG64ImmToFp(fd int, v int64) ([]byte, error) {
+	if v < -2048 || v > 4095 {
+		return nil, fmt.Errorf("MOVW $%d: immediate out of the [-2048, 4095] range for an F register destination", v)
 	}
-	mov := uint32(0x452a << 10) // movgr2fr.d
-	if mnem == "MOVF" {
-		mov = 0x4529 << 10 // movgr2fr.w
+	op := uint32(0x00a << 22) // addi.w r30, r0, v (sign-extends)
+	if v > 0 {
+		op = 0x00e << 22 // ori r30, r0, v (zero-extends)
 	}
 	return l64WordsLE(
 		l64irr(op, int(v), 0, 30),
-		l64rr(mov, 30, fd),
-	)
+		l64rr(0x4529<<10, 30, fd), // movgr2fr.w fd, r30
+	), nil
 }
 
 // ---- 64-bit immediate classification ----

asm/loong64_encode.go

@@ -199,7 +199,9 @@ func l64rrrr(op uint32, r1, r2, r3, r4 int) uint32 {
 }
 
 // l64irir encodes a BSTRINS/BSTRPICK instruction: op | msb<<16 | rj<<5 | lsb<<10 | rd.
-// The msb/lsb fields are 6 bits wide (0-63) and are validated by the caller.
+// The msb/lsb fields are 6 bits wide and are inserted unmasked: the caller
+// must have validated them (0..31 for the .w forms, 0..63 for the .d forms,
+// lsb <= msb), the same rule the toolchain enforces as "illegal bit number".
 func l64irir(op uint32, msb, rj, lsb, rd int) uint32 {
 	return op | uint32(msb)<<16 | uint32(rj&0x1f)<<5 | uint32(lsb)<<10 | uint32(rd&0x1f)
 }

asm/loong64_encode_test.go

@@ -319,11 +319,11 @@ TEXT ·f(SB), NOSPLIT, $0-0
 `)
 	code = assembleLOONG64Helper(t, fn)
 	wantWords(t, code,
-		0x29FFE061, // addi.d r1, r2, -8 (prologue)
-		0x02FFE063, // addi.d r3, r3, -8
-		0x29C00061, // st.d r1, r2, 0 (prologue saves RA)
+		0x29FFE061, // st.d r1, -8(r3) (prologue saves RA below the new SP)
+		0x02FFE063, // addi.d r3, r3, -8 (prologue opens the frame)
+		0x29C00061, // st.d r1, 0(r3) (prologue saves RA at SP)
 		0x4C0000A1, // jirl r1, r5, 0
-		0x28C00061, // ld.d r1, r2, 0 (epilogue restores RA)
+		0x28C00061, // ld.d r1, 0(r3) (epilogue restores RA)
 		0x02C02063, // addi.d r3, r3, 8
 		0x4C000020, // jirl r0, r1, 0 (RET)
 	)

asm/loong64_more_test.go

@@ -347,21 +347,94 @@ TEXT ·sb(SB), NOSPLIT, $0
 	}
 }
 
-// TestLOONG64_movImmToFp checks the immediate-to-FP move forms.
+// TestLOONG64_movImmToFp checks the immediate-to-FP move: MOVW $c, Fd is the
+// only spelling the toolchain accepts, expanding to ori (or addi.w for the
+// negative span) into R30 plus movgr2fr.w.  The pinned words are the
+// toolchain's own bytes; the other widths and out-of-range constants are
+// illegal combinations there and are diagnosed here.
 func TestLOONG64_movImmToFp(t *testing.T) {
 	fn := firstTextLOONG64(t, `#include "textflag.h"
 TEXT ·fpmov(SB), NOSPLIT, $0
-	MOVV $0x1, F0
+	MOVW $0x1, F0
 	MOVW $0x2, F4
+	MOVW $-1, F4
 	RET
 `)
 	code := assembleLOONG64Helper(t, fn)
 	want := []byte{
-		0x00, 0x04, 0x80, 0x03, // ori f0, r0, 1
-		0x04, 0x08, 0x80, 0x03, // ori f4, r0, 2
+		0x1e, 0x04, 0x80, 0x03, // ori r30, r0, 1
+		0xc0, 0xa7, 0x14, 0x01, // movgr2fr.w f0, r30
+		0x1e, 0x08, 0x80, 0x03, // ori r30, r0, 2
+		0xc4, 0xa7, 0x14, 0x01, // movgr2fr.w f4, r30
+		0x1e, 0xfc, 0xbf, 0x02, // addi.w r30, r0, -1
+		0xc4, 0xa7, 0x14, 0x01, // movgr2fr.w f4, r30
 		0x20, 0x00, 0x00, 0x4c, // jirl r0, r1, 0
 	}
 	if !bytes.Equal(code, want) {
 		t.Errorf("code = % x\nwant % x", code, want)
 	}
 }
+
+// TestLOONG64_movImmToFpErrors checks the immediate-to-FP diagnostics: the
+// widths the toolchain rejects as illegal combinations, and constants beyond
+// the 12-bit ori/addi.w span (the toolchain never materialises a wider
+// constant on this path).
+func TestLOONG64_movImmToFpErrors(t *testing.T) {
+	cases := []string{
+		"MOVV $1, F0",
+		"MOVF $2, F4",
+		"MOVD $2, F4",
+		"MOVW $100000, F1",
+		"MOVW $-2049, F1",
+		"MOVW $4096, F1",
+	}
+	for _, src := range cases {
+		fn := firstTextLOONG64(t, "#include \"textflag.h\"\nTEXT ·e(SB), NOSPLIT, $0\n\t"+src+"\n\tRET\n")
+		if _, _, _, _, _, err := assembleLOONG64(fn); err == nil {
+			t.Errorf("%s: expected an error, got none", src)
+		}
+	}
+}
+
+// TestLOONG64_branch16Unsigned pins the unsigned two-operand branches: with
+// one register BLTU/BGEU keep the register-register form against R0 (never
+// taken), the toolchain's encoding, where a beqz would test the wrong
+// condition; the three-operand forms are unchanged.
+func TestLOONG64_branch16Unsigned(t *testing.T) {
+	fn := firstTextLOONG64(t, `#include "textflag.h"
+TEXT ·u(SB), NOSPLIT, $0
+	BLTU R4, done
+	BGEU R5, done
+	BLTU R6, R7, done
+	BGEU R8, R9, done
+done:
+	RET
+`)
+	code := assembleLOONG64Helper(t, fn)
+	wantWords(t, code,
+		0x68001080, // bltu r4, r0, +4
+		0x6C000CA0, // bgeu r5, r0, +3
+		0x680008C7, // bltu r6, r7, +2
+		0x6C000509, // bgeu r8, r9, +1
+		0x4C000020, // jirl r0, r1, 0
+	)
+}
+
+// TestLOONG64_bitFieldRange checks the BSTRINS/BSTRPICK bit-number
+// validation, mirroring the toolchain's "illegal bit number" rule: 0..31 for
+// the .w forms, 0..63 for the .d forms, and lsb <= msb.
+func TestLOONG64_bitFieldRange(t *testing.T) {
+	cases := []string{
+		"BSTRINSW $32, R4, $0, R5",
+		"BSTRPICKW $31, R4, $32, R5",
+		"BSTRINSV $64, R4, $0, R5",
+		"BSTRPICKV $3, R4, $4, R5",
+		"BSTRINSW $-1, R4, $0, R5",
+	}
+	for _, src := range cases {
+		fn := firstTextLOONG64(t, "#include \"textflag.h\"\nTEXT ·e(SB), NOSPLIT, $0\n\t"+src+"\n\tRET\n")
+		if _, _, _, _, _, err := assembleLOONG64(fn); err == nil {
+			t.Errorf("%s: expected an error, got none", src)
+		}
+	}
+}

asm/riscv_assemble.go

@@ -15,7 +15,10 @@ import (
 func assembleRISCV(t *ast.Text) ([]byte, map[string]int, []Reloc, []LineEntry, []SpadjStep, error) {
 	fi := riscvComputeFrame(t)
 	prologue := riscvPrologue(fi)
-	guardLen := riscvGuardLen(fi)
+	guardLen, err := riscvGuardLen(fi)
+	if err != nil {
+		return nil, nil, nil, nil, nil, err
+	}
 
 	var relocs []Reloc
 	var spadj []SpadjStep
@@ -66,20 +69,20 @@ func assembleRISCV(t *ast.Text) ([]byte, map[string]int, []Reloc, []LineEntry, [
 		}
 	}
 
-	// Pass 4: recompute offsets with actual sizes.
+	// Pass 4: recompute offsets with actual sizes.  recs holds the
+	// instructions in emission order, so an index into it walks t.Body in
+	// lockstep (the same single pass Pass 1 uses) instead of rescanning the
+	// whole slice per statement.
 	offsets = map[string]int{}
 	pos = guardLen + len(prologue)
+	ri := 0
 	for _, stmt := range t.Body {
 		switch s := stmt.(type) {
 		case *ast.Label:
 			offsets[s.Name.Text] = pos
 		case *ast.Instr:
-			for _, r := range recs {
-				if r.instr == s {
-					pos += len(r.code)
-					break
-				}
-			}
+			pos += len(recs[ri].code)
+			ri++
 		}
 	}
 
@@ -89,7 +92,10 @@ func assembleRISCV(t *ast.Text) ([]byte, map[string]int, []Reloc, []LineEntry, [
 	// the morestack block at the end of the function, which the previous
 	// passes have sized.
 	var out []byte
-	guardBytes, guardReloc := riscvGuard(fi)
+	guardBytes, guardReloc, err := riscvGuard(fi)
+	if err != nil {
+		return nil, nil, nil, nil, nil, err
+	}
 	if fi.needSplit {
 		out = append(out, guardBytes...)
 	}
@@ -231,6 +237,25 @@ func isBranchLike(mnem string) bool {
 	return false
 }
 
+// riscvCheckBranchOffset rejects a B-type displacement outside its signed
+// 13-bit span [-4096, 4094]; the encoder masks to 13 bits, so an
+// out-of-range offset would otherwise wrap to a wrong target.
+func riscvCheckBranchOffset(target string, off int32) error {
+	if off < -4096 || off > 4094 {
+		return fmt.Errorf("branch to %q too far (13-bit range)", target)
+	}
+	return nil
+}
+
+// riscvCheckJumpOffset rejects a J-type displacement outside its signed
+// 21-bit span [-1048576, 1048574].
+func riscvCheckJumpOffset(target string, off int32) error {
+	if off < -1048576 || off > 1048574 {
+		return fmt.Errorf("jump to %q too far (21-bit range)", target)
+	}
+	return nil
+}
+
 // encodeRISCVInstr encodes a single RISC-V instruction.
 func encodeRISCVInstr(instr *ast.Instr, pc int, offsets map[string]int, fi riscvFrameInfo, relocs *[]Reloc) ([]byte, error) {
 	mnem := instr.Mnemonic.Text
@@ -304,6 +329,9 @@ func encodeRISCVInstr(instr *ast.Instr, pc int, offsets map[string]int, fi riscv
 			return nil, fmt.Errorf("undefined label %q%s", target, suggestLabel(target, offsets))
 		}
 		offset := int32(targetOff - pc)
+		if err := riscvCheckJumpOffset(target, offset); err != nil {
+			return nil, err
+		}
 		word = riscvJType(0, offset)
 		return []byte{byte(word), byte(word >> 8), byte(word >> 16), byte(word >> 24)}, nil
 	case "JAL":
@@ -320,6 +348,9 @@ func encodeRISCVInstr(instr *ast.Instr, pc int, offsets map[string]int, fi riscv
 			return nil, fmt.Errorf("undefined label %q%s", target, suggestLabel(target, offsets))
 		}
 		offset := int32(targetOff - pc)
+		if err := riscvCheckJumpOffset(target, offset); err != nil {
+			return nil, err
+		}
 		word = riscvJType(rd, offset)
 		return []byte{byte(word), byte(word >> 8), byte(word >> 16), byte(word >> 24)}, nil
 
@@ -365,6 +396,9 @@ func encodeRISCVInstr(instr *ast.Instr, pc int, offsets map[string]int, fi riscv
 		case "BGTZ":
 			enc, rs1, rs2 = riscvEnc{0x63, 0x4, 0x00}, 0, rs // blt x0, rs
 		}
+		if err := riscvCheckBranchOffset(target, int32(targetOff-pc)); err != nil {
+			return nil, err
+		}
 		word = riscvBType(enc, rs1, rs2, int32(targetOff-pc))
 		return []byte{byte(word), byte(word >> 8), byte(word >> 16), byte(word >> 24)}, nil
 
@@ -374,7 +408,14 @@ func encodeRISCVInstr(instr *ast.Instr, pc int, offsets map[string]int, fi riscv
 		if !ok {
 			return nil, fmt.Errorf("unsupported system instruction %q", mnem)
 		}
-		word = riscvIType(enc, 0, 0, 0)
+		// The bare FENCE expands to fence iorw, iorw: the predecessor and
+		// successor fields both carry 0xF in the I-type immediate
+		// (the toolchain's encodeFenceOperand TYPE_NONE default).
+		imm := int32(0)
+		if mnem == "FENCE" {
+			imm = 0x0FF
+		}
+		word = riscvIType(enc, 0, 0, imm)
 		return []byte{byte(word), byte(word >> 8), byte(word >> 16), byte(word >> 24)}, nil
 	}
 
@@ -416,7 +457,10 @@ func encodeRISCVInstr(instr *ast.Instr, pc int, offsets map[string]int, fi riscv
 			return nil, fmt.Errorf("%s expects 3 operands, got %d", mnem, len(ops))
 		}
 		csr := immFromOperand(ops[0]) // CSR address (12-bit)
-		rd := regFromOperand(ops[2])  // destination register
+		if csr < 0 || csr > 0xFFF {
+			return nil, fmt.Errorf("%s: CSR address %d out of range 0-0xFFF", mnem, csr)
+		}
+		rd := regFromOperand(ops[2]) // destination register
 		if rd < 0 {
 			return nil, fmt.Errorf("invalid destination register in %s", mnem)
 		}
@@ -561,9 +605,9 @@ func encodeRISCVInstr(instr *ast.Instr, pc int, offsets map[string]int, fi riscv
 	// I-type with immediate: Plan 9 order is INSTR $imm, rs1, rd; the
 	// two-operand form INSTR $imm, rd uses rd as the source.
 	case len(ops) == 3 && isITypeInstr(mnem):
-		imm := immFromOperand(ops[0]) // immediate
-		if immNeg {
-			imm = -imm // SUB $imm arrived through the ADDI alias
+		imm, err := riscvImm32FromOperand(ops[0], immNeg) // immediate
+		if err != nil {
+			return nil, err
 		}
 		rs1 := regFromOperand(ops[1]) // source register
 		rd := regFromOperand(ops[2])  // destination
@@ -573,9 +617,9 @@ func encodeRISCVInstr(instr *ast.Instr, pc int, offsets map[string]int, fi riscv
 		return encodeRISCVItypeImmediate(mnem, enc, rd, rs1, imm)
 
 	case len(ops) == 2 && isITypeInstr(mnem):
-		imm := immFromOperand(ops[0])
-		if immNeg {
-			imm = -imm
+		imm, err := riscvImm32FromOperand(ops[0], immNeg)
+		if err != nil {
+			return nil, err
 		}
 		rd := regFromOperand(ops[1])
 		if rd < 0 {
@@ -614,6 +658,9 @@ func encodeRISCVInstr(instr *ast.Instr, pc int, offsets map[string]int, fi riscv
 		if rs1 < 0 || rs2 < 0 {
 			return nil, fmt.Errorf("invalid register in %s", mnem)
 		}
+		if err := riscvCheckBranchOffset(target, offset); err != nil {
+			return nil, err
+		}
 
 		// The Go assembler never compresses branches to C.BEQZ/C.BNEZ.
 		word = riscvBType(enc, rs1, rs2, offset)
@@ -695,7 +742,10 @@ func encodeRISCVMov(instr *ast.Instr, fi riscvFrameInfo, relocs *[]Reloc) ([]byt
 		if rd < 0 {
 			return nil, fmt.Errorf("MOV $imm: invalid destination register")
 		}
-		imm := immFromOperand(src)
+		imm, err := riscvImm32FromOperand(src, false)
+		if err != nil {
+			return nil, err
+		}
 		return encodeRISCVLoadImm(rd, imm), nil
 	}
 
@@ -1081,7 +1131,7 @@ func encodeRISCVJALR(instr *ast.Instr, fi riscvFrameInfo) ([]byte, error) {
 // tryCompressRVC attempts to compress a RISC-V instruction to its 16-bit
 // RVC form.  It returns the compressed instruction word and true on success.
 func tryCompressRVC(instr *ast.Instr, fi riscvFrameInfo) (uint16, bool) {
-	mnem := instr.Mnemonic.Text
+	mnem := riscvCompressMnem(instr)
 	ops := instr.Operands
 
 	switch mnem {
@@ -1331,6 +1381,49 @@ func tryCompressRVC(instr *ast.Instr, fi riscvFrameInfo) (uint16, bool) {
 	return 0, false
 }
 
+// riscvCompressMnem maps a MOV-family load or store onto the base mnemonic
+// the toolchain lowers it to (MOVW 4(SP), X9 is LW under another name), so
+// the width spellings compress exactly like their base forms.  Register and
+// immediate forms keep their own mnemonic: the C.MV path matches "MOV" and
+// nothing else in the switch has a width case.
+func riscvCompressMnem(instr *ast.Instr) string {
+	mnem := instr.Mnemonic.Text
+	ops := instr.Operands
+	if !strings.HasPrefix(mnem, "MOV") || len(ops) != 2 {
+		return mnem
+	}
+	load := isMemOperand(ops[0]) && !isMemOperand(ops[1])
+	store := !isMemOperand(ops[0]) && isMemOperand(ops[1])
+	if !load && !store {
+		return mnem
+	}
+	switch mnem {
+	case "MOVW":
+		if load {
+			return "LW"
+		}
+		return "SW"
+	case "MOVF":
+		if load {
+			return "FLW"
+		}
+		return "FSW"
+	case "MOVD":
+		if load {
+			return "FLD"
+		}
+		return "FSD"
+	case "MOV":
+		if load {
+			return "LD"
+		}
+		return "SD"
+	}
+	// MOVB/MOVBU/MOVH/MOVHU/MOVWU have no compressed form; their base
+	// mnemonics (LB/LBU/LH/LHU/LWU, SB/SH) match no case either.
+	return mnem
+}
+
 // extractLDParams extracts rd, rs1, and immediate offset for a load instruction.
 func extractLDParams(instr *ast.Instr, fi riscvFrameInfo) (rd, rs1 int, imm int32) {
 	ops := instr.Operands
@@ -1507,6 +1600,29 @@ func immFromOperand(op *ast.Operand) int32 {
 	return 0
 }
 
+// riscvImm32FromOperand reads an immediate for the MOV/I-type paths as a
+// signed 32-bit value.  The toolchain materialises wider constants through
+// its SLLI expansion, which this assembler does not implement, so values
+// outside the int32 span are diagnosed instead of silently truncated (MOV
+// $0x123456789 must not assemble as $0x3456789).  The neg flag carries the
+// SUB $imm alias, whose negated value may fit when the written one does not.
+func riscvImm32FromOperand(op *ast.Operand, neg bool) (int32, error) {
+	var v int64
+	if op.Imm.HasVal {
+		v = op.Imm.Val
+		if op.Imm.Neg {
+			v = -v
+		}
+	}
+	if neg {
+		v = -v
+	}
+	if int64(int32(v)) != v {
+		return 0, fmt.Errorf("immediate %d out of range; 64-bit materialisation not supported", v)
+	}
+	return int32(v), nil
+}
+
 func memFromOperand(op *ast.Operand) (rs1 int, imm int32) {
 	rs1 = riscvRegNum(op.Addr.Base)
 	imm = int32(op.Addr.Offset)

asm/riscv_encode.go

@@ -65,7 +65,7 @@ func riscvRegNum(name string) int {
 		return 25
 	case "X26", "S10":
 		return 26
-	case "X27", "S11":
+	case "X27", "S11", "g":
 		return 27
 	case "X28", "T3":
 		return 28
@@ -373,7 +373,7 @@ var riscvFmaTable = map[string]riscvFmaEnc{
 // riscvFmaType encodes an R4-type fused multiply-add instruction.
 func riscvFmaType(enc riscvFmaEnc, rd, rs1, rs2, rs3 int) uint32 {
 	return (uint32(rs3) << 27) | (enc.fmt << 25) | (uint32(rs2) << 20) |
-		(uint32(rs1) << 15) | (0x0 << 12) /* rm=dynamic */ | (uint32(rd) << 7) | enc.opcode
+		(uint32(rs1) << 15) | (0x0 << 12) /* rm=RNE */ | (uint32(rd) << 7) | enc.opcode
 }
 
 // CSR (Control and Status Register) instructions.
@@ -522,11 +522,13 @@ func rvcCL(funct3, rd, rs1 uint32, imm uint32) uint16 {
 
 // rvcCS encodes a register-relative compressed store (op=00 quadrant): C.SW
 // (funct3=6), C.SD (funct3=7) or C.FSD (funct3=5).  imm is the full byte
-// offset; the immediate bits are extracted per the RISC-V CS format.
+// offset; the immediate bits are extracted per the RISC-V CS format, with the
+// same five-bit patterns as the load side ({5,4,3,7,6} and {5,4,3,2,6},
+// matching the toolchain's encodeCS).
 func rvcCS(funct3, rs2, rs1 uint32, imm uint32) uint16 {
-	pattern := []int{5, 3, 7, 6}
+	pattern := []int{5, 4, 3, 7, 6}
 	if funct3 == 0x6 {
-		pattern = []int{5, 3, 2, 6}
+		pattern = []int{5, 4, 3, 2, 6}
 	}
 	packed := encodeRVCPattern(imm, pattern)
 	return uint16((funct3 << 13) | ((packed>>2)&0x7)<<10 | (rs1 << 7) | ((packed & 0x3) << 5) | (rs2 << 2))

asm/riscv_encode_test.go

@@ -5,6 +5,7 @@ package asm
 
 import (
 	"bytes"
+	"strings"
 	"testing"
 
 	"sourcedock.dev/petrbalvin/gasm-devkit/ast"
@@ -691,6 +692,81 @@ DATA answer<>+0(SB)/8, $42
 	}
 }
 
+// TestRISCV_RVC_StorePatterns pins the register-relative compressed store
+// encodings for offsets with immediate bits 4 and 5 set, byte-identical to
+// the toolchain's encodeCS (patterns {5,4,3,7,6} and {5,4,3,2,6}).
+// Regression: the store-side patterns dropped imm[4], so every such store
+// silently encoded the wrong address while the loads stayed correct.
+func TestRISCV_RVC_StorePatterns(t *testing.T) {
+	fn := firstTextRISCV(t, `#include "textflag.h"
+TEXT ·csstores(SB), NOSPLIT, $0
+	SD  X9, 24(X8)
+	SW  X10, 16(X11)
+	FSD F8, 40(X12)
+	LD  24(X8), X9
+	LW  16(X11), X10
+	FLD 40(X12), F8
+	RET
+`)
+	code := assembleRISCVHelper(t, fn)
+	want := []byte{
+		0x04, 0xec, // c.sd x9, 24(x8)
+		0x88, 0xc9, // c.sw x10, 16(x11)
+		0x00, 0xb6, // c.fsd f8, 40(x12)
+		0x04, 0x6c, // c.ld x9, 24(x8)
+		0x88, 0x49, // c.lw x10, 16(x11)
+		0x00, 0x36, // c.fld f8, 40(x12)
+		0x67, 0x80, 0x00, 0x00, // jalr x0, 0(x1)
+	}
+	if !bytes.Equal(code, want) {
+		t.Errorf("code = % x\nwant % x", code, want)
+	}
+}
+
+// TestRISCV_FENCE pins the FENCE encoding: the toolchain expands the bare
+// mnemonic to fence iorw, iorw (0x0FF0000F), not fence 0,0.
+func TestRISCV_FENCE(t *testing.T) {
+	fn := firstTextRISCV(t, `#include "textflag.h"
+TEXT ·fence(SB), NOSPLIT, $0
+	FENCE
+	RET
+`)
+	code := assembleRISCVHelper(t, fn)
+	want := []byte{
+		0x0f, 0x00, 0xf0, 0x0f, // fence iorw, iorw
+		0x67, 0x80, 0x00, 0x00, // jalr x0, 0(x1)
+	}
+	if !bytes.Equal(code, want) {
+		t.Errorf("code = % x\nwant % x", code, want)
+	}
+}
+
+// TestRISCV_RVC_WidthSpellings pins the compression of the GOROOT width
+// spellings: MOVW and MOVD lower to their base load/store and compress
+// exactly like LW/SW/FLD/FSD would (the toolchain compresses these shapes;
+// before the normalisation they stayed 4 bytes).
+func TestRISCV_RVC_WidthSpellings(t *testing.T) {
+	fn := firstTextRISCV(t, `#include "textflag.h"
+TEXT ·widths(SB), NOSPLIT, $0-16
+	MOVW w+0(FP), X9
+	MOVW X9, v+4(FP)
+	MOVD d+0(FP), F8
+	MOVD F8, r+8(FP)
+	RET
+`)
+	code := assembleRISCVHelper(t, fn)
+	want := []byte{
+		0xa2, 0x44, // c.lwsp x9, 8
+		0x26, 0xc6, // c.swsp x9, 12
+		0x22, 0x24, // c.fldsp f8, 8
+		0x22, 0xa8, // c.fsdsp f8, 16
+		0x67, 0x80, 0x00, 0x00, // jalr x0, 0(x1)
+	}
+	if !bytes.Equal(code, want) {
+		t.Errorf("code = % x\nwant % x", code, want)
+	}
+}
+
 func TestRISCV_system_instrs(t *testing.T) {
 	// Test FENCE, ECALL, EBREAK encoding.
 	fn := firstTextRISCV(t, `#include "textflag.h"
@@ -782,3 +858,116 @@ TEXT ·f(SB), NOSPLIT, $0-0
 		0x00008067, // jalr x0, 1(x0), 0 (RET)
 	)
 }
+
+// encodeOneInstrRISCV encodes a single parsed instruction against a synthetic
+// offsets map, the smallest honest harness for the branch-range diagnostics:
+// the spans are far larger than any source a test would want to spell out.
+func encodeOneInstrRISCV(t *testing.T, src string, pc int, offsets map[string]int) ([]byte, error) {
+	t.Helper()
+	fn := firstTextRISCV(t, "#include \"textflag.h\"\n"+src)
+	instr := fn.Body[0].(*ast.Instr)
+	return encodeRISCVInstr(instr, pc, offsets, riscvFrameInfo{}, nil)
+}
+
+// TestRISCVBranchJumpRange checks that displacements beyond the B-type span
+// [-4096, 4094] and the J-type span [-1048576, 1048574] are diagnosed instead
+// of wrapping silently to a wrong target.
+func TestRISCVBranchJumpRange(t *testing.T) {
+	cases := []struct {
+		name string
+		src  string
+		off  int // the target's function-relative offset (pc 0)
+		ok   bool
+	}{
+		{"branch max", "BEQ X10, X11, tgt\nRET\n", 4094, true},
+		{"branch past max", "BEQ X10, X11, tgt\nRET\n", 4096, false},
+		{"branch back max", "BEQ X10, X11, tgt\nRET\n", -4096, true},
+		{"branch back past max", "BEQ X10, X11, tgt\nRET\n", -4098, false},
+		{"branchz past max", "BEQZ X10, tgt\nRET\n", 4096, false},
+		{"jump max", "JMP tgt\nRET\n", 1048574, true},
+		{"jump past max", "JMP tgt\nRET\n", 1048576, false},
+		{"jump back max", "JMP tgt\nRET\n", -1048576, true},
+		{"jump back past max", "JMP tgt\nRET\n", -1048578, false},
+		{"jal past max", "JAL tgt\nRET\n", 1048576, false},
+	}
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			_, err := encodeOneInstrRISCV(t, "TEXT ·f(SB), NOSPLIT, $0\n\t"+c.src, 0, map[string]int{"tgt": c.off})
+			if c.ok && err != nil {
+				t.Fatalf("unexpected error: %v", err)
+			}
+			if !c.ok && err == nil {
+				t.Fatal("expected an out-of-range diagnostic, got none")
+			}
+		})
+	}
+}
+
+// TestRISCVBranchFarBody drives the range check through the full two-pass
+// assembler: a forward branch over a body larger than the B-type span must
+// error rather than wrap.
+func TestRISCVBranchFarBody(t *testing.T) {
+	var sb strings.Builder
+	sb.WriteString("#include \"textflag.h\"\nTEXT ·far(SB), NOSPLIT, $0\n\tBEQ X10, X11, done\n")
+	for range 1100 {
+		sb.WriteString("\tADD X10, X11, X12\n")
+	}
+	sb.WriteString("done:\n\tRET\n")
+	fn := firstTextRISCV(t, sb.String())
+	if _, _, _, _, _, err := assembleRISCV(fn); err == nil {
+		t.Error("expected a branch-out-of-range error, got none")
+	}
+}
+
+// TestRISCV_CSRRange checks the CSR address range: the 12-bit field is
+// diagnosed rather than masked, so CSRRW $4096 does not silently address
+// CSR 0.
+func TestRISCV_CSRRange(t *testing.T) {
+	fn := firstTextRISCV(t, `#include "textflag.h"
+TEXT ·csrhi(SB), NOSPLIT, $0
+	CSRRW $4096, X10, X11
+	RET
+`)
+	if _, _, _, _, _, err := assembleRISCV(fn); err == nil {
+		t.Error("expected an out-of-range error for CSR $4096, got none")
+	}
+	fn = firstTextRISCV(t, `#include "textflag.h"
+TEXT ·csrmax(SB), NOSPLIT, $0
+	CSRRW $4095, X10, X11
+	RET
+`)
+	if _, _, _, _, _, err := assembleRISCV(fn); err != nil {
+		t.Errorf("CSR $4095 must assemble: %v", err)
+	}
+}
+
+// TestRISCV_Imm64Rejected checks that immediates outside the signed 32-bit
+// span are diagnosed instead of silently truncated to their low 32 bits (the
+// toolchain materialises such constants via SLLI expansion, which this
+// assembler does not implement).
+func TestRISCV_Imm64Rejected(t *testing.T) {
+	cases := []string{
+		"MOV $0x123456789, X10",
+		"ADDI $0x100000000, X10, X11",
+		"ANDI $-0x800000001, X10, X11",
+		"SUB $0x100000000, X10, X11",
+	}
+	for _, src := range cases {
+		fn := firstTextRISCV(t, "#include \"textflag.h\"\nTEXT ·wide(SB), NOSPLIT, $0\n\t"+src+"\n\tRET\n")
+		if _, _, _, _, _, err := assembleRISCV(fn); err == nil {
+			t.Errorf("%s: expected an out-of-range error, got none", src)
+		}
+	}
+	// The full signed 32-bit span still assembles, including the SUB form
+	// whose negated immediate only just fits.
+	fn := firstTextRISCV(t, `#include "textflag.h"
+TEXT ·edge(SB), NOSPLIT, $0
+	MOV  $2147483647, X10
+	MOV  $-2147483648, X11
+	SUB  $0x80000000, X12, X13
+	RET
+`)
+	if _, _, _, _, _, err := assembleRISCV(fn); err != nil {
+		t.Errorf("int32-span immediates must assemble: %v", err)
+	}
+}

asm/riscv_frame.go

@@ -4,6 +4,7 @@
 package asm
 
 import (
+	"fmt"
 	"strings"
 
 	"sourcedock.dev/petrbalvin/gasm-devkit/ast"
@@ -241,33 +242,36 @@ func riscvFitsCAddi(imm int32) bool {
 }
 
 // riscvPrologueSpadjPC returns the function-relative byte offset where the
-// prologue has finished decrementing SP (the delta becomes autosize).
+// prologue has finished decrementing SP (the delta becomes autosize).  It is
+// computed from the same expansion functions the prologue emits, so the
+// large-frame X31 materialisations are counted: C.LUI + C.ADD before the SD,
+// C.LUI + ADDIW + C.ADD for the SP adjust.
 func riscvPrologueSpadjPC(fi riscvFrameInfo) int {
 	if fi.autosize == 0 {
 		return 0
 	}
-	// SD (4 bytes) + ADDI/C.ADDI (2 or 4 bytes).
-	return 4 + riscvSPAdjustLen(int32(-fi.autosize))
+	adj := int32(-fi.autosize)
+	if fits12(adj) {
+		// SD (4 bytes) + ADDI/C.ADDI (2 or 4 bytes).
+		return 4 + len(riscvSPAdjust(adj))
+	}
+	return len(riscvAddressInX31(adj)) + 4 + len(riscvAddToSP(adj))
 }
 
 // riscvReturnEpilogueLen returns the byte length of the RET's epilogue up to
-// (but not including) the final JALR, the point where SP is restored.
+// (but not including) the final JALR, the point where SP is restored.  The
+// small frame closes with C.LDSP + ADDI/C.ADDI; the large frame materialises
+// the adjustment through X31 (C.LUI + ADDIW + C.ADD).
 func riscvReturnEpilogueLen(fi riscvFrameInfo) int {
 	if fi.autosize == 0 {
 		return 0
 	}
-	// C.LDSP (2 bytes) + ADDI/C.ADDI (2 or 4 bytes).
-	return 2 + riscvSPAdjustLen(int32(fi.autosize))
-}
-
-func riscvSPAdjustLen(imm int32) int {
-	if imm != 0 && imm%16 == 0 && imm >= -512 && imm <= 511 {
-		return 2
+	adj := int32(fi.autosize)
+	if fits12(adj) {
+		// C.LDSP (2 bytes) + ADDI/C.ADDI (2 or 4 bytes).
+		return 2 + len(riscvSPAdjust(adj))
 	}
-	if riscvFitsCAddi(imm) {
-		return 2
-	}
-	return 4
+	return 2 + len(riscvAddToSP(adj))
 }
 
 // riscvResolvePseudo translates a pseudo-register memory reference into a
@@ -293,19 +297,21 @@ func riscvResolvePseudo(sym *ast.Symbol, fi riscvFrameInfo) (base int, off int32
 // including the inline morestack call (zero when the function needs no
 // guard).  Unlike amd64 and arm64, the toolchain places the morestack call
 // between the guard and the body: the guard branches forward over it.
-func riscvGuardLen(fi riscvFrameInfo) int {
-	_, reloc := riscvGuard(fi)
-	_ = reloc
-	return len(riscvGuardBytes(fi))
+func riscvGuardLen(fi riscvFrameInfo) (int, error) {
+	g, _, err := riscvGuard(fi)
+	if err != nil {
+		return 0, err
+	}
+	return len(g), nil
 }
 
 // riscvGuard emits the stack-split guard prefix with the inline morestack
 // call: the branch skips forward over JAL X5 and JAL X0 straight into the
 // body; the JAL X5 carries the R_RISCV_JAL relocation.  All offsets are
 // relative to the guard itself, which sits at function offset 0.
-func riscvGuard(fi riscvFrameInfo) ([]byte, Reloc) {
+func riscvGuard(fi riscvFrameInfo) ([]byte, Reloc, error) {
 	if !fi.needSplit {
-		return nil, Reloc{}
+		return nil, Reloc{}, nil
 	}
 	// MOV 16(g), X6 (g.stackguard0), g = X27.
 	out := wordLE(riscvIType(riscvEnc{0x03, 0x3, 0x00}, 6, 27, 16))
@@ -317,14 +323,14 @@ func riscvGuard(fi riscvFrameInfo) ([]byte, Reloc) {
 	var reloc Reloc
 	switch fi.splitClass {
 	case 0:
-		// BLTU X6, SP, done (+8: over the CALL and the JMP back)
+		// BLTU X6, SP, done (+12: over the CALL and the JMP back)
 		out = append(out, wordLE(riscvBType(riscvEnc{0x63, 0x06, 0x00}, 6, 2, 12))...)
 		call := len(out)
 		reloc = Reloc{Off: call, After: call + 4, Name: "runtime\u00b7morestack_noctxt", Kind: RelRISCVJal}
 		out = append(out, wordLE(riscvJType(5, 0))...)
 		out = append(out, jalBack()...)
 	case 1:
-		// ADDI $-(framesize-StackSmall), SP, X7; BLTU X6, X7, done (+8)
+		// ADDI $-(framesize-StackSmall), SP, X7; BLTU X6, X7, done (+12)
 		off := int32(fi.autosize - stackSmall)
 		out = append(out, wordLE(riscvIType(riscvEnc{0x13, 0x0, 0x00}, 7, 2, -off))...)
 		out = append(out, wordLE(riscvBType(riscvEnc{0x63, 0x06, 0x00}, 6, 7, 12))...)
@@ -342,7 +348,10 @@ func riscvGuard(fi riscvFrameInfo) ([]byte, Reloc) {
 		out = append(out, wordLE(riscvBType(riscvEnc{0x63, 0x06, 0x00}, 2, 7, int32(addiLen+8)))...)
 		addi, err := encodeRISCVItypeImmediate("ADDI", riscvEnc{0x13, 0x0, 0x00}, 7, 2, -off)
 		if err != nil {
-			addi = nil
+			// The ADDI expansion failed: the SP adjustment this class
+			// depends on is not emittable, and silently dropping it would
+			// corrupt every stack reference in the body.
+			return nil, Reloc{}, fmt.Errorf("stack-split guard: %w", err)
 		}
 		out = append(out, addi...)
 		out = append(out, wordLE(riscvBType(riscvEnc{0x63, 0x06, 0x00}, 6, 7, 12))...)
@@ -351,11 +360,5 @@ func riscvGuard(fi riscvFrameInfo) ([]byte, Reloc) {
 		out = append(out, wordLE(riscvJType(5, 0))...)
 		out = append(out, jalBack()...)
 	}
-	return out, reloc
-}
-
-// riscvGuardBytes emits the guard prefix bytes alone (sizing helper).
-func riscvGuardBytes(fi riscvFrameInfo) []byte {
-	g, _ := riscvGuard(fi)
-	return g
+	return out, reloc, nil
 }

asm/riscv_frame_test.go

@@ -65,6 +65,47 @@ TEXT ·framed(SB), NOSPLIT, $16-16
 	}
 }
 
+// TestRISCVFrameSpadjLargeFrame checks the stack-adjustment boundaries of a
+// frame past the imm12 range: the prologue materialises the LR-store address
+// and the SP adjustment through X31 (C.LUI + C.ADD + SD, then C.LUI + ADDIW +
+// C.ADD), so the SP boundary lands at PC 16, and the RET closes with
+// C.LDSP plus the same X31 adjustment, 10 bytes.  Regression: both helpers
+// assumed the small-frame prologue and reported 8 and 6.
+func TestRISCVFrameSpadjLargeFrame(t *testing.T) {
+	f, errs := parser.Parse("bigframe_riscv64.s", `#include "textflag.h"
+
+TEXT ·big(SB), NOSPLIT, $9000-8
+	MOV a+0(FP), X10
+	RET
+`)
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFileRISCV(f)
+	if err != nil {
+		t.Fatalf("AssembleFileRISCV: %v", err)
+	}
+	fn := img.Funcs[0]
+
+	// autosize = 9008.  Prologue: C.LUI X31 + C.ADD X31,SP (4) + SD (4) +
+	// C.LUI X31 + ADDIW X31 + C.ADD SP,X31 (8) = 16 bytes to the SP boundary;
+	// C.SDSP X1 (2) follows, so the body starts at 18.
+	wantSpadj := []SpadjStep{{PC: 16, Value: 9008}, {PC: 36, Value: 0}}
+	if len(fn.Spadj) != len(wantSpadj) {
+		t.Fatalf("spadj = %v, want %v", fn.Spadj, wantSpadj)
+	}
+	for i := range wantSpadj {
+		if fn.Spadj[i] != wantSpadj[i] {
+			t.Errorf("spadj[%d] = %v, want %v", i, fn.Spadj[i], wantSpadj[i])
+		}
+	}
+	// The FP load materialises its 9016-byte offset through X31 as well
+	// (8 bytes), then RET's epilogue (C.LDSP + X31 adjust = 10) plus JALR.
+	if fn.Size != 18+8+14 {
+		t.Errorf("size = %d, want %d", fn.Size, 18+8+14)
+	}
+}
+
 // TestRISCVRegAliases checks the Go ABI register aliases that the toolchain
 // defines: LR is the link register (X1) and TMP is the assembler scratch
 // register (X31/T6).

asm/riscv_goobj_test.go

@@ -74,6 +74,89 @@ DATA callee<>+0(SB)/8, $42
 		t.Error("ELF object missing R_RISCV_JAL relocation")
 	}
 }
+
+// TestELFRISCVPCRELLO12Anchor checks the psABI's LO12 pairing rule: the
+// R_RISCV_PCREL_LO12_I/S relocation must reference a symbol whose value is
+// the AUIPC site of its HI20 partner (psABI §8.4.9; cmd/link generates one
+// local text symbol per AUIPC for exactly this).  The emitter pairs each
+// HI20 (against the target symbol) with a LO12 against the .text section
+// symbol whose addend is the AUIPC's section-relative offset, so S + A is
+// the AUIPC address.
+func TestELFRISCVPCRELLO12Anchor(t *testing.T) {
+	f, errs := parser.Parse("k_riscv64.s", `
+#include "textflag.h"
+
+TEXT ·sb(SB), NOSPLIT, $0-0
+	MOV $answer<>(SB), X10
+	MOV answer<>(SB), X11
+	MOV X12, answer<>(SB)
+	RET
+
+GLOBL answer<>(SB), RODATA, $8
+DATA answer<>+0(SB)/8, $42
+`)
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFileRISCV(f)
+	if err != nil {
+		t.Fatalf("AssembleFileRISCV: %v", err)
+	}
+	obj, err := img.ELFRISCVObject()
+	if err != nil {
+		t.Fatalf("ELFRISCVObject: %v", err)
+	}
+	ef, err := elf.NewFile(bytes.NewReader(obj))
+	if err != nil {
+		t.Fatalf("parse ELF: %v", err)
+	}
+	defer ef.Close()
+	if flags := binary.LittleEndian.Uint32(obj[48:]); flags != efRISCVFloatAbiDouble {
+		t.Errorf("e_flags = %#x, want %#x (EF_RISCV_FLOAT_ABI_DOUBLE)", flags, efRISCVFloatAbiDouble)
+	}
+	rela := ef.Section(".rela.text")
+	if rela == nil {
+		t.Fatal("missing .rela.text")
+	}
+	b, err := rela.Data()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(b) != 6*24 {
+		t.Fatalf(".rela.text holds %d entries, want six (three HI20/LO12 pairs)", len(b)/24)
+	}
+	le := binary.LittleEndian
+	wantLo := []uint32{rRISCVPCRELLO12I, rRISCVPCRELLO12I, rRISCVPCRELLO12S}
+	for p := range 3 {
+		auipc := 8 * p
+		hi := b[p*2*24:]
+		lo := b[(p*2+1)*24:]
+		if off := le.Uint64(hi[0:]); off != uint64(auipc) {
+			t.Errorf("pair %d: HI20 r_offset = %d, want %d (the AUIPC)", p, off, auipc)
+		}
+		if typ := uint32(le.Uint64(hi[8:])); typ != rRISCVPCRELHI20 {
+			t.Errorf("pair %d: HI20 type = %d, want %d", p, typ, rRISCVPCRELHI20)
+		}
+		if sym := int(le.Uint64(hi[8:]) >> 32); sym == 0 || sym == 1 {
+			t.Errorf("pair %d: HI20 against symbol %d, want the target", p, sym)
+		}
+		if off := le.Uint64(lo[0:]); off != uint64(auipc+4) {
+			t.Errorf("pair %d: LO12 r_offset = %d, want %d", p, off, auipc+4)
+		}
+		if typ := uint32(le.Uint64(lo[8:])); typ != wantLo[p] {
+			t.Errorf("pair %d: LO12 type = %d, want %d", p, typ, wantLo[p])
+		}
+		// The LO12 must denote the AUIPC site: the .text section symbol
+		// (index 1) plus the AUIPC's section-relative offset as addend.
+		if sym := int(le.Uint64(lo[8:]) >> 32); sym != 1 {
+			t.Errorf("pair %d: LO12 against symbol %d, want 1 (the .text section symbol)", p, sym)
+		}
+		if add := int64(le.Uint64(lo[16:])); add != int64(auipc) {
+			t.Errorf("pair %d: LO12 addend = %d, want %d (S + A = the AUIPC address)", p, add, auipc)
+		}
+	}
+}
+
 func TestGOObjectRISCVStructure(t *testing.T) {
 	f, errs := parser.Parse("k_riscv64.s", `
 #include "textflag.h"

ast/ast.go

@@ -114,6 +114,7 @@ type Symbol struct {
 	Pkg    string // package prefix before the middle dot ("" = current package)
 	Name   string // identifier without the middle dot or <>
 	Static bool   // the <> marker is present
+	ABI    string // the <NAME> ABI marker, e.g. ABIInternal ("" when absent)
 	Pseudo string // FP, SP, SB or PC ("" for a bare name)
 	Offset int64
 	HasOff bool
@@ -156,5 +157,5 @@ type Address struct {
 	Scale  int     // index scale; 0 when absent
 	Offset int64   // leading displacement, from off(base)
 	HasOff bool    // a leading displacement is present
-	Shift  string  // verbatim arm64 shift suffix, e.g. "<<2"
+	Shift  string  // verbatim arm64 shift suffix, e.g. "<< 2"
 }

cmd/gasm/audit.go

@@ -40,10 +40,13 @@ func cmdAuditInstructions(args []string) error {
 	fs := newCommand("audit-instructions", "gasm audit-instructions [--corpus [dir]] [amd64|arm64|riscv64|loong64]", `
 Compare the gasm encoder for the given architecture (default amd64) against
 go tool asm and print the diff: superset encodings (gasm-only, shippable via
-gasm asm --format goobj), known-but-unencodable names (the backlog) and go-
-only names (feature gaps).  The Go side is probed black-box with a battery
-of bare mnemonics, so the audit tracks whatever toolchain `+"`go env GOROOT`"+`
-provides.
+gasm asm --format goobj) and known-but-unencodable names (the backlog).  The
+Go side is probed black-box one bare mnemonic at a time, so the audit tracks
+whatever toolchain `+"`go env GOROOT`"+` provides; the gasm side answers from
+the encoder table on amd64 and from trial assembly over a battery of operand
+shapes elsewhere.  Names go tool asm knows and gasm does not cannot be
+enumerated by probing, because Go's table is visible only through names
+already in the gasm table; the report closes with a note saying so.
 
 With --corpus the audit changes shape: it assembles every .s file under the
 given directory (default GOROOT/src) with the gasm encoder only, no
@@ -63,7 +66,7 @@ the encodability backlog by frequency rather than by table order.
 	archName := "amd64"
 	switch n := len(fs.Args()); {
 	case n > 1:
-		return fmt.Errorf("audit-instructions takes at most one architecture argument")
+		return &usageError{fmt.Errorf("audit-instructions takes at most one architecture argument")}
 	case n == 1:
 		archName = strings.ToLower(fs.Arg(0))
 	}
@@ -109,7 +112,7 @@ the encodability backlog by frequency rather than by table order.
 
 	w := os.Stdout
 	fmt.Fprintf(w, "gasm table (%s, families excluded): %d mnemonics\n", archName, len(names))
-	fmt.Fprintf(w, "gasm encodable: %d   go tool asm recognized: %d\n", len(shared)+len(superset), countTrue(goKnown))
+	fmt.Fprintf(w, "gasm encodable: %d   go tool asm recognised: %d\n", len(shared)+len(superset), countTrue(goKnown))
 	fmt.Fprintf(w, "shared: %d\n", len(shared))
 	fmt.Fprintf(w, "\nSuperset encodings (gasm-only; ship via gasm asm --format goobj):\n")
 	for _, n := range superset {
@@ -136,7 +139,7 @@ func auditArch(name string) (arch.Arch, error) {
 	case "loong64", "loong":
 		return arch.LOONG64, nil
 	}
-	return arch.Unknown, fmt.Errorf("unknown architecture %q: want amd64, arm64, riscv64 or loong64", name)
+	return arch.Unknown, &usageError{fmt.Errorf("unknown architecture %q: want amd64, arm64, riscv64 or loong64", name)}
 }
 
 // goarchName maps an arch identifier onto its GOARCH spelling.
@@ -217,6 +220,13 @@ func probeGoAsm(goarch string, names []string) (map[string]bool, error) {
 	cmd := exec.Command(asmBin, "-p", "probe", "-o", filepath.Join(dir, "probe.o"), probePath)
 	cmd.Env = append(os.Environ(), "GOARCH="+goarch, "GOOS="+runtime.GOOS)
 	out, _ := cmd.CombinedOutput()
+	// The expected failure mode is a non-zero exit with compiler diagnostics
+	// on stdout; empty output means the probe broke at the exec level (a
+	// killed child, a tool that would not start), and seeding every name as
+	// recognized on that silence would fake a clean audit.
+	if len(out) == 0 {
+		return nil, fmt.Errorf("go tool asm probe for GOARCH=%s produced no output", goarch)
+	}
 
 	result := map[string]bool{}
 	for _, name := range names {
@@ -344,7 +354,7 @@ func (t *corpusTally) fail(path, reason string) {
 // cmdAuditCorpus implements audit-instructions --corpus.
 func cmdAuditCorpus(args []string) error {
 	if len(args) > 1 {
-		return fmt.Errorf("audit-instructions --corpus takes at most one directory argument")
+		return &usageError{fmt.Errorf("audit-instructions --corpus takes at most one directory argument")}
 	}
 	root := ""
 	if len(args) == 1 {

cmd/gasm/debug_linux.go

@@ -24,9 +24,10 @@ function in a traced subprocess (ptrace), then provides a REPL for
 single-stepping, breakpoints, register and memory inspection.
 
 REPL commands:
-  break <label|addr> [if <reg> <op> <val>]
+  break <label|addr|line> [if <reg> <op> <val|reg|*addr>]
                        set a breakpoint, optionally conditional on a
-                       register comparison (reg-reg or reg-immediate)
+                       comparison of one register against a constant,
+                       another register, or the 8-byte word at *addr
   delete <label|addr>  remove a breakpoint
   info break           list all breakpoints
   step [n], s          single-step n instructions (default 1)
@@ -53,7 +54,7 @@ REPL commands:
 	bufSpec := fs.String("buf", "", "buffer specification: name:size:pattern[,name:size:pattern...] where pattern is zero, ones, seq, or hex")
 	script := fs.String("script", "", "run REPL commands from a file (one per line) and exit; '-' reads stdin")
 	cover := fs.Bool("cover", false, "run to completion with a breakpoint on every instruction and report which executed and how often")
-	timeout := fs.Duration("timeout", 0, "kill the debuggee after this duration (e.g. 30s); for headless --script runs")
+	timeout := fs.Duration("timeout", 0, "kill the debuggee after this duration (e.g. 30s); for headless --script runs; a timeout exits 3")
 	fs.Parse(args)
 
 	// --- Debuggee mode (internal, spawned by the debugger) ---
@@ -231,6 +232,13 @@ REPL commands:
 			if sess.Exited() {
 				break
 			}
+			// A genuine signal-delivery-stop (a fault in the kernel): the
+			// run cannot make progress, because resuming would restart the
+			// faulting instruction and fault forever.  Report and stop.
+			if sig := sess.LastSignal(); sig != 0 {
+				fmt.Printf("gasm debug: cover: stopped on signal %v\n", sig)
+				break
+			}
 			regs, rerr := sess.GetRegs()
 			if rerr != nil {
 				break

cmd/gasm/main.go

@@ -10,6 +10,7 @@ package main
 import (
 	"bytes"
 	"encoding/json"
+	"errors"
 	"flag"
 	"fmt"
 	"io"
@@ -48,6 +49,22 @@ func version() string {
 	return bi.Main.Version
 }
 
+// usageError marks an error the caller's arguments caused, which exits 2
+// instead of the 1 a runtime failure gets.
+type usageError struct{ err error }
+
+func (e *usageError) Error() string { return e.err.Error() }
+func (e *usageError) Unwrap() error { return e.err }
+
+// exitCodeFor maps an error onto the process exit status: 2 for a usage
+// error, 1 for anything else.
+func exitCodeFor(err error) int {
+	if _, ok := errors.AsType[*usageError](err); ok {
+		return 2
+	}
+	return 1
+}
+
 func main() {
 	if len(os.Args) < 2 {
 		usage(os.Stderr)
@@ -77,12 +94,12 @@ func main() {
 	case "audit-instructions":
 		if err := cmdAuditInstructions(os.Args[2:]); err != nil {
 			fmt.Fprintln(os.Stderr, err)
-			os.Exit(1)
+			os.Exit(exitCodeFor(err))
 		}
 	case "scaffold":
 		if err := cmdScaffold(os.Args[2:]); err != nil {
 			fmt.Fprintln(os.Stderr, err)
-			os.Exit(1)
+			os.Exit(exitCodeFor(err))
 		}
 	case "lsp":
 		os.Exit(cmdLSP(os.Args[2:]))
@@ -104,11 +121,11 @@ func cmdVersion() int {
 
 // ANSI colour helpers for terminal output.
 const (
-	colorReset  = "\033[0m"
-	colorBold   = "\033[1m"
-	colorCyan   = "\033[36m"
-	colorYellow = "\033[33m"
-	colorGray   = "\033[90m"
+	colourReset  = "\033[0m"
+	colourBold   = "\033[1m"
+	colourCyan   = "\033[36m"
+	colourYellow = "\033[33m"
+	colourGrey   = "\033[90m"
 )
 
 // isTTY reports whether the writer is a terminal (for colour output).
@@ -122,9 +139,9 @@ func isTTY(w io.Writer) bool {
 
 func usage(w io.Writer) {
 	useColor := isTTY(w)
-	bold, cyan, yellow, gray, reset := "", "", "", "", ""
+	bold, cyan, yellow, grey, reset := "", "", "", "", ""
 	if useColor {
-		bold, cyan, yellow, gray, reset = colorBold, colorCyan, colorYellow, colorGray, colorReset
+		bold, cyan, yellow, grey, reset = colourBold, colourCyan, colourYellow, colourGrey, colourReset
 	}
 
 	fmt.Fprintf(w, "%sgasm %s%s: developer tooling for Go's Plan 9 assembler (GAsm)%s\n\n", bold, version(), reset, reset)
@@ -153,12 +170,12 @@ func usage(w io.Writer) {
 		{"version", "print the version (same as --version)"},
 	}
 	for _, c := range commands {
-		fmt.Fprintf(w, "  %s%-10s%s %s%s%s\n", cyan, c.name, reset, gray, c.desc, reset)
+		fmt.Fprintf(w, "  %s%-10s%s %s%s%s\n", cyan, c.name, reset, grey, c.desc, reset)
 	}
 
 	fmt.Fprintf(w, "\n%sFlags:%s\n", yellow, reset)
-	fmt.Fprintf(w, "  %s-h, --help%s      %sshow this help%s\n", cyan, reset, gray, reset)
-	fmt.Fprintf(w, "  %s-V, --version%s   %sprint the version%s\n", cyan, reset, gray, reset)
+	fmt.Fprintf(w, "  %s-h, --help%s      %sshow this help%s\n", cyan, reset, grey, reset)
+	fmt.Fprintf(w, "  %s-V, --version%s   %sprint the version%s\n", cyan, reset, grey, reset)
 
 	fmt.Fprintf(w, "\nRun \"gasm <command> -h\" for a command's usage and flags.\n\n")
 
@@ -172,7 +189,7 @@ func usage(w io.Writer) {
 	}
 	for _, e := range examples {
 		if e.desc != "" {
-			fmt.Fprintf(w, "  %s%s%s  %s%s%s\n", cyan, e.cmd, reset, gray, e.desc, reset)
+			fmt.Fprintf(w, "  %s%s%s  %s%s%s\n", cyan, e.cmd, reset, grey, e.desc, reset)
 		} else {
 			fmt.Fprintf(w, "  %s%s%s\n", cyan, e.cmd, reset)
 		}
@@ -469,10 +486,13 @@ func cmdAsm(args []string) int {
 With -o the output is written to a file instead.  The --format flag selects
 what is written: raw (the default) concatenates the functions and the data
 section into one self-consistent image; elf emits a relocatable object
-(.text/.data sections, a symbol table and one PC32 relocation per
-static-symbol reference) that links with the system toolchain; goobj emits
-the Go toolchain's own object format, which cmd/link consumes directly (it
-requires -p, the package path, and the installed Go toolchain).
+(.text/.data sections, a symbol table and one relocation per static-symbol
+reference, in the architecture's own form: R_X86_64_PC32 on amd64,
+R_AARCH64_*, R_RISCV_* or R_LARCH_* on the others) that links with the
+system toolchain; goobj emits the Go toolchain's own object format, which
+cmd/link consumes directly (it requires -p, the package path, and the
+installed Go toolchain: the object preamble is captured from go tool asm
+and the format version from go version).
 `)
 	out := fs.String("o", "", "write the output to this file")
 	format := fs.String("format", "raw", "output format: raw (concatenated image), elf or goobj (Go object)")
@@ -483,6 +503,14 @@ requires -p, the package path, and the installed Go toolchain).
 		fmt.Fprintln(os.Stderr, "usage: gasm asm [--format raw|elf|goobj] [-p pkg] [-GOARCH arch] [-o out] <file>")
 		return 2
 	}
+	// The format is validated before anything else, so a bogus value exits 2
+	// with or without -o instead of silently dumping the hex of a raw image.
+	switch *format {
+	case "raw", "elf", "goobj":
+	default:
+		fmt.Fprintf(os.Stderr, "gasm asm: unknown format %q (want raw, elf or goobj)\n", *format)
+		return 2
+	}
 	path := fs.Arg(0)
 	targetArch := arch.FromFilename(path)
 	if *archName != "" {
@@ -517,38 +545,42 @@ requires -p, the package path, and the installed Go toolchain).
 		fmt.Fprintln(os.Stderr, "gasm asm: no assemblable TEXT functions or GLOBL data found")
 		return 1
 	}
-	for _, fn := range img.Funcs {
-		code := img.Code[fn.Offset : fn.Offset+fn.Size]
-		fmt.Printf("%s: %d bytes\n", fn.Name, fn.Size)
-		for i := 0; i < len(code); i += 16 {
-			end := min(i+16, len(code))
-			fmt.Printf("  %04x:", i)
-			for _, b := range code[i:end] {
-				fmt.Printf(" %02x", b)
+	// Without -o the hex dump on stdout is the output; with -o the file is,
+	// and the dump is skipped, as the -o help text promises.
+	if *out == "" {
+		for _, fn := range img.Funcs {
+			code := img.Code[fn.Offset : fn.Offset+fn.Size]
+			fmt.Printf("%s: %d bytes\n", fn.Name, fn.Size)
+			for i := 0; i < len(code); i += 16 {
+				end := min(i+16, len(code))
+				fmt.Printf("  %04x:", i)
+				for _, b := range code[i:end] {
+					fmt.Printf(" %02x", b)
+				}
+				fmt.Println()
 			}
-			fmt.Println()
 		}
-	}
-	if len(img.Data) > 0 {
-		fmt.Printf("data: %d bytes at 0x%x\n", len(img.Data), len(img.Code))
-		for _, d := range f.Decls {
-			g, ok := d.(*ast.Globl)
-			if !ok || g.Name == nil || g.Name.Pseudo != "SB" {
-				continue
+		if len(img.Data) > 0 {
+			fmt.Printf("data: %d bytes at 0x%x\n", len(img.Data), len(img.Code))
+			for _, d := range f.Decls {
+				g, ok := d.(*ast.Globl)
+				if !ok || g.Name == nil || g.Name.Pseudo != "SB" {
+					continue
+				}
+				size := 0
+				if g.Size != nil && g.Size.Imm.HasVal {
+					size = int(g.Size.Imm.Val)
+				}
+				fmt.Printf("  %s: %d bytes at 0x%x\n", g.Name.Name, size, img.Symbols[g.Name.Name])
 			}
-			size := 0
-			if g.Size != nil && g.Size.Imm.HasVal {
-				size = int(g.Size.Imm.Val)
+			for i := 0; i < len(img.Data); i += 16 {
+				end := min(i+16, len(img.Data))
+				fmt.Printf("  %04x:", len(img.Code)+i)
+				for _, b := range img.Data[i:end] {
+					fmt.Printf(" %02x", b)
+				}
+				fmt.Println()
 			}
-			fmt.Printf("  %s: %d bytes at 0x%x\n", g.Name.Name, size, img.Symbols[g.Name.Name])
-		}
-		for i := 0; i < len(img.Data); i += 16 {
-			end := min(i+16, len(img.Data))
-			fmt.Printf("  %04x:", len(img.Code)+i)
-			for _, b := range img.Data[i:end] {
-				fmt.Printf(" %02x", b)
-			}
-			fmt.Println()
 		}
 	}
 	if *out != "" {
@@ -586,9 +618,6 @@ requires -p, the package path, and the installed Go toolchain).
 				obj, err = img.GOObject(*pkg, path)
 			}
 			kind = "Go object"
-		default:
-			fmt.Fprintf(os.Stderr, "gasm asm: unknown format %q (want raw, elf or goobj)\n", *format)
-			return 2
 		}
 		if err != nil {
 			fmt.Fprintln(os.Stderr, "gasm asm:", err)
@@ -767,8 +796,8 @@ func cmdProfile(args []string) int {
 	flagSet := newCommand("profile", "gasm profile <file.s>", `
 Show the basic-block structure of functions in an assembly file.
 Lists each function's labels, their offsets, and the block boundaries.
-This is the static structure; for runtime execution counts, use
-gasm verify --fuzz which exercises the code paths.
+This is the static structure; for runtime execution counts use
+gasm debug --cover, and for input coverage gasm verify --fuzz.
 `)
 	flagSet.Parse(args)
 	if flagSet.NArg() != 1 {
@@ -912,11 +941,40 @@ func compareGroundTruth(img *asm.Image, gt map[string][]byte) (matched, total, d
 				goCmp[j] = 0
 			}
 		}
-		if bytes.Equal(gasmCmp, goCmp) {
+		// The toolchain pads text symbols to 16-byte boundaries with
+		// zeros, so a function whose size is not a multiple of 16
+		// carries trailing zeros in the ground truth that are not part
+		// of the encoding.  Compare up to the shorter side and require
+		// the remainder of whichever is longer to be zero, so padding
+		// never masks a real difference.
+		cmpLen := min(len(gasmCmp), len(goCmp))
+		equal := bytes.Equal(gasmCmp[:cmpLen], goCmp[:cmpLen])
+		if equal {
+			for _, b := range gasmCmp[cmpLen:] {
+				if b != 0 {
+					equal = false
+					break
+				}
+			}
+		}
+		if equal {
+			for _, b := range goCmp[cmpLen:] {
+				if b != 0 {
+					equal = false
+					break
+				}
+			}
+		}
+		if equal {
 			matched++
-			if len(fn.Relocs) > 0 {
+			switch {
+			case len(fn.Relocs) > 0 && len(goCmp) > cmpLen:
+				fmt.Printf("  %s: MATCH (%d bytes, %d relocs masked, %d padding)\n", fn.Name, fn.Size, len(fn.Relocs), len(goCmp)-cmpLen)
+			case len(fn.Relocs) > 0:
 				fmt.Printf("  %s: MATCH (%d bytes, %d relocs masked)\n", fn.Name, fn.Size, len(fn.Relocs))
-			} else {
+			case len(goCmp) > cmpLen:
+				fmt.Printf("  %s: MATCH (%d bytes, %d padding)\n", fn.Name, fn.Size, len(goCmp)-cmpLen)
+			default:
 				fmt.Printf("  %s: MATCH (%d bytes)\n", fn.Name, fn.Size)
 			}
 		} else {
@@ -964,8 +1022,8 @@ that tolerate nil pointers and zero lengths in their arguments.
 With -abi, each function is called with sentinel values in the registers
 the Go ABI fixes across calls (the frame pointer and the goroutine
 pointer) plus a canary below SP; violations are reported.  JIT-based
-checks run when the host matches the file's architecture (all but
-loong64, which is ground-truth only for now).
+checks run when the host matches the file's architecture, on all four
+architectures.
 
 With -fuzz, each function with a // func signature is differentially fuzzed
 against the go-tool-asm version in a subprocess (so a crash on a partial
@@ -978,7 +1036,8 @@ With -profile, the static basic-block structure is listed for each function.
 
 With -call, a single function is invoked with user-supplied buffers (-buf)
 instead of the smoke/abi/fuzz sweeps.  Useful for partial functions (e.g.
-decoders) that crash on random input but should succeed on valid data.
+decoders) that crash on random input but should succeed on valid data.  The
+function named must be NOSPLIT: a function with a stack frame is refused.
 
 With -save-corpus (and -fuzz), every input that crashes or mismatches is
 written to the directory as replayable JSON.  -replay re-runs saved
@@ -1007,20 +1066,16 @@ each entry reproduces.
 	path := set.Arg(0)
 	targetArch := arch.FromFilename(path)
 	// JIT execution runs when the host CPU matches the kernel's
-	// architecture, except loong64: its trampoline is implemented but not
-	// yet validated against real hardware (the Go runtime cannot start
-	// under the available loong64 emulators), so those kernels take the
-	// toolchain-comparison path.
-	if targetArch != hostArch() || targetArch == arch.LOONG64 {
-		// No JIT on this host: ground truth and profile remain available.
-		// (loong64 is ground-truth-only everywhere for now: its trampoline
-		// is implemented but not yet validated against real hardware.)
+	// architecture; every trampoline is validated end to end under
+	// qemu-user emulation (the loong64 one included, via the raw-address
+	// leave handoff).
+	if targetArch != hostArch() {
+		// No JIT on this host: ground truth and profile remain available for
+		// every architecture, because cmdVerifyNonJIT assembles and compares
+		// against the toolchain without executing anything.
 		switch targetArch {
-		case arch.RISCV, arch.LOONG64, arch.ARM64:
+		case arch.AMD64, arch.RISCV, arch.LOONG64, arch.ARM64:
 			return cmdVerifyNonJIT(path, targetArch, *groundTruth, *profile)
-		case arch.AMD64:
-			fmt.Fprintln(os.Stderr, "gasm verify: JIT-based checks need an amd64 host; use --ground-truth here")
-			return 1
 		default:
 			fmt.Fprintln(os.Stderr, "gasm verify: unsupported architecture")
 			return 1

cmd/gasm/main_test.go

@@ -13,6 +13,9 @@ import (
 	"strings"
 	"syscall"
 	"testing"
+
+	"sourcedock.dev/petrbalvin/gasm-devkit/arch"
+	"sourcedock.dev/petrbalvin/gasm-devkit/asm"
 )
 
 const clean = "#include \"textflag.h\"\n" +
@@ -242,6 +245,96 @@ func TestCmdArgErrors(t *testing.T) {
 	}
 }
 
+// TestUsageExitCodes pins the exit-code contract for the commands whose main
+// dispatches on a returned error: a wrong argument set exits 2, the same as
+// the commands that count their arguments themselves, while a runtime
+// failure (an unreadable file) keeps exit 1.
+func TestUsageExitCodes(t *testing.T) {
+	for name, err := range map[string]error{
+		"audit-instructions extra argument": cmdAuditInstructions([]string{"amd64", "extra"}),
+		"audit-instructions unknown arch":   cmdAuditInstructions([]string{"mips"}),
+		"audit-instructions corpus extra":   cmdAuditInstructions([]string{"--corpus", "a", "b"}),
+		"scaffold no arguments":             cmdScaffold(nil),
+		"scaffold extra arguments":          cmdScaffold([]string{"differential", "a.s", "b.s"}),
+	} {
+		if err == nil {
+			t.Errorf("%s: expected an error", name)
+			continue
+		}
+		if code := exitCodeFor(err); code != 2 {
+			t.Errorf("%s: exit code = %d, want 2 (err: %v)", name, code, err)
+		}
+	}
+	if err := cmdScaffold([]string{"differential", "/nonexistent/file.s"}); err == nil {
+		t.Error("scaffold on a missing file should fail")
+	} else if code := exitCodeFor(err); code != 1 {
+		t.Errorf("scaffold on a missing file: exit code = %d, want 1", code)
+	}
+}
+
+// TestCmdAsmFormatValidation checks that an unknown --format exits 2 with
+// and without -o, instead of assembling and silently dumping a raw image.
+func TestCmdAsmFormatValidation(t *testing.T) {
+	path := writeTemp(t, "f_amd64.s", clean)
+	out := filepath.Join(t.TempDir(), "f.bin")
+	if _, _, code := capture(func() int { return cmdAsm([]string{"--format", "bogus", path}) }); code != 2 {
+		t.Errorf("asm --format bogus without -o: code = %d, want 2", code)
+	}
+	if _, _, code := capture(func() int { return cmdAsm([]string{"--format", "bogus", "-o", out, path}) }); code != 2 {
+		t.Errorf("asm --format bogus with -o: code = %d, want 2", code)
+	}
+}
+
+// TestCmdAsmOutputFile pins the documented -o behaviour: the output goes to
+// the file and stdout carries no hex dump; without -o the dump is the output.
+func TestCmdAsmOutputFile(t *testing.T) {
+	path := writeTemp(t, "f_amd64.s", clean)
+	out := filepath.Join(t.TempDir(), "f.bin")
+	stdout, _, code := capture(func() int { return cmdAsm([]string{"-o", out, path}) })
+	if code != 0 {
+		t.Fatalf("code = %d", code)
+	}
+	if strings.Contains(stdout, "0000:") {
+		t.Errorf("stdout carries a hex dump despite -o:\n%s", stdout)
+	}
+	if !strings.Contains(stdout, "wrote ") {
+		t.Errorf("stdout misses the wrote line:\n%s", stdout)
+	}
+	b, err := os.ReadFile(out)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(b) == 0 {
+		t.Error("the output file is empty")
+	}
+
+	stdout, _, code = capture(func() int { return cmdAsm([]string{path}) })
+	if code != 0 {
+		t.Fatalf("without -o: code = %d", code)
+	}
+	if !strings.Contains(stdout, "0000:") {
+		t.Errorf("without -o the hex dump is missing:\n%s", stdout)
+	}
+}
+
+// TestVerifyNonJITAMD64GroundTruth drives the cross-architecture
+// ground-truth path for an amd64 kernel: the path a host of any other
+// architecture takes, which must compare against the toolchain rather than
+// refuse to run.
+func TestVerifyNonJITAMD64GroundTruth(t *testing.T) {
+	if testing.Short() {
+		t.Skip("runs go tool asm")
+	}
+	path := writeTemp(t, "f_amd64.s", clean)
+	out, _, code := capture(func() int { return cmdVerifyNonJIT(path, arch.AMD64, true, false) })
+	if code != 0 {
+		t.Fatalf("code = %d (%s)", code, out)
+	}
+	if !strings.Contains(out, "1/1 matched") {
+		t.Errorf("output misses the matched report:\n%s", out)
+	}
+}
+
 // TestVerifySmokeCrashIsolation checks that a function faulting on its
 // zeroed smoke arguments is reported as CRASH by a child process instead of
 // killing `gasm verify` itself.
@@ -348,3 +441,22 @@ func TestRunCorpusAudit(t *testing.T) {
 		t.Errorf("arm64 unencodable reasons = %d, want 1", r)
 	}
 }
+
+// TestCompareGroundTruthPadding pins the padding-aware ground-truth
+// comparison: the toolchain pads text symbols to 16-byte boundaries, so
+// trailing zeros in the reference must not read as a mismatch, while any
+// non-zero tail still must.
+func TestCompareGroundTruthPadding(t *testing.T) {
+	code := []byte{0x48, 0x8b, 0x07, 0xc3} // 4 bytes, not a multiple of 16
+	img := &asm.Image{Code: code, Funcs: []asm.FuncLayout{{Name: "f", Offset: 0, Size: len(code)}}}
+	padded := append(append([]byte(nil), code...), 0, 0, 0)
+	matched, total, diffs := compareGroundTruth(img, map[string][]byte{"f": padded})
+	if matched != 1 || total != 1 || diffs != 0 {
+		t.Fatalf("zero padding should match: matched=%d total=%d diffs=%d", matched, total, diffs)
+	}
+	dirty := append(append([]byte(nil), code...), 0, 0x90, 0)
+	matched, _, diffs = compareGroundTruth(img, map[string][]byte{"f": dirty})
+	if matched != 0 || diffs != 1 {
+		t.Fatalf("non-zero padding must mismatch: matched=%d diffs=%d", matched, diffs)
+	}
+}

cmd/gasm/man_test.go

@@ -62,6 +62,42 @@ func TestManPagesTrackTheCLI(t *testing.T) {
 	}
 }
 
+// TestManCommandsTrackHelp compares the gasm(1) COMMANDS list with the
+// top-level help output, so a subcommand added to the binary cannot miss
+// its man entry and a stale entry cannot outlive its command.
+func TestManCommandsTrackHelp(t *testing.T) {
+	if testing.Short() {
+		t.Skip("builds the gasm binary")
+	}
+	bin := filepath.Join(t.TempDir(), "gasm")
+	if out, err := exec.Command("go", "build", "-o", bin, ".").CombinedOutput(); err != nil {
+		t.Fatalf("build gasm: %v\n%s", err, out)
+	}
+
+	raw, err := os.ReadFile(filepath.Join("..", "..", "docs", "man", "gasm.1"))
+	if err != nil {
+		t.Fatalf("read man page: %v", err)
+	}
+
+	helpOut, err := exec.Command(bin, "--help").Output()
+	if err != nil {
+		t.Fatalf("gasm --help: %v", err)
+	}
+
+	binCmds := helpCommands(string(helpOut))
+	pageCmds := roffCommands(string(raw))
+	for c := range binCmds {
+		if !pageCmds[c] {
+			t.Errorf("command %q is in the binary's help but missing from gasm(1) COMMANDS", c)
+		}
+	}
+	for c := range pageCmds {
+		if !binCmds[c] {
+			t.Errorf("command %q is in gasm(1) COMMANDS but the binary does not list it", c)
+		}
+	}
+}
+
 // helpFlags extracts the flag names from a `gasm <cmd> -h` output.
 func helpFlags(help string) map[string]bool {
 	m := map[string]bool{}
@@ -123,6 +159,54 @@ func roffFlags(page string) map[string]bool {
 	return m
 }
 
+// helpCommands extracts the command names from the top-level help output's
+// Commands section.
+func helpCommands(help string) map[string]bool {
+	m := map[string]bool{}
+	inCmds := false
+	for line := range strings.SplitSeq(help, "\n") {
+		if strings.TrimSpace(line) == "Commands:" {
+			inCmds = true
+			continue
+		}
+		if !inCmds {
+			continue
+		}
+		t := strings.TrimSpace(line)
+		if t == "" {
+			break
+		}
+		name, _, _ := strings.Cut(t, " ")
+		m[name] = true
+	}
+	return m
+}
+
+// roffCommands extracts the command names from gasm(1)'s COMMANDS section,
+// where each entry is written as `.B gasm\-<name>(1)` or `.B gasm <name>`.
+func roffCommands(page string) map[string]bool {
+	m := map[string]bool{}
+	inCmds := false
+	for line := range strings.SplitSeq(page, "\n") {
+		if strings.HasPrefix(line, ".SH ") {
+			inCmds = strings.HasPrefix(line, ".SH COMMANDS")
+			continue
+		}
+		if !inCmds || !strings.HasPrefix(line, ".B gasm") {
+			continue
+		}
+		entry := strings.ReplaceAll(strings.TrimPrefix(line, ".B "), `\-`, "-")
+		entry = strings.TrimSuffix(entry, "(1)")
+		switch {
+		case strings.HasPrefix(entry, "gasm-"):
+			m[strings.TrimPrefix(entry, "gasm-")] = true
+		case strings.HasPrefix(entry, "gasm "):
+			m[strings.TrimPrefix(entry, "gasm ")] = true
+		}
+	}
+	return m
+}
+
 // helpUsage returns the command's usage line without the "Usage: " prefix.
 func helpUsage(help string) string {
 	for line := range strings.SplitSeq(help, "\n") {

cmd/gasm/scaffold.go

@@ -44,7 +44,7 @@ bodies, place the file in the kernel's package, and run it in CI.
 		rest = rest[1:]
 	}
 	if len(rest) != 1 {
-		return fmt.Errorf("usage: gasm scaffold differential <file.s>")
+		return &usageError{fmt.Errorf("usage: gasm scaffold differential <file.s>")}
 	}
 	path := rest[0]
 	src, err := os.ReadFile(path)

debug/breakpoint.go

@@ -9,11 +9,11 @@ import "strings"
 
 import "fmt"
 
-// Breakpoint is one INT3 breakpoint in the debuggee.
+// Breakpoint is one software breakpoint in the debuggee.
 type Breakpoint struct {
 	Addr    uint64 // absolute address in the debuggee
 	Label   string // source label ("" for raw addresses)
-	Orig    byte   // original byte at Addr (restored on removal)
+	Orig    []byte // original bytes at Addr (restored on removal)
 	Enabled bool
 	Cond    *Condition // optional condition (nil = unconditional)
 	hits    int
@@ -32,8 +32,12 @@ type Condition struct {
 	MemAddr uint64 // memory address (for register-memory comparison, prefixed with *)
 }
 
-// Eval checks the condition against the current registers.
-func (c *Condition) Eval(regs *Regs) bool {
+// Eval checks the condition against the current registers.  For the
+// register-memory form, mem reads an 8-byte little-endian word from the
+// debuggee; it may be nil when no reader is available.  Anything that cannot
+// be decided (unknown register or operator, unreadable memory) does not
+// block the breakpoint.
+func (c *Condition) Eval(regs *Regs, mem func(addr uint64) (uint64, bool)) bool {
 	actual, ok := regs.RegValue(c.Reg)
 	if !ok {
 		return true // unknown register, don't block
@@ -48,9 +52,16 @@ func (c *Condition) Eval(regs *Regs) bool {
 		}
 		expected = v
 	case c.MemAddr != 0:
-		// Register-memory comparison, requires a Session, not available here.
-		// Fall back to treating as constant (the caller should resolve).
-		expected = c.Value
+		// Register-memory comparison, resolved in the debuggee at
+		// evaluation time.
+		if mem == nil {
+			return true
+		}
+		v, ok := mem(c.MemAddr)
+		if !ok {
+			return true
+		}
+		expected = v
 	default:
 		expected = c.Value
 	}
@@ -72,6 +83,18 @@ func (c *Condition) Eval(regs *Regs) bool {
 	}
 }
 
+// String renders the condition for display.
+func (c *Condition) String() string {
+	switch {
+	case c.Reg2 != "":
+		return fmt.Sprintf("%s %s %s", c.Reg, c.Op, c.Reg2)
+	case c.MemAddr != 0:
+		return fmt.Sprintf("%s %s *%#x", c.Reg, c.Op, c.MemAddr)
+	default:
+		return fmt.Sprintf("%s %s %#x", c.Reg, c.Op, c.Value)
+	}
+}
+
 // Breakpoints manages the software breakpoints of one Session.
 type Breakpoints struct {
 	t   tracer
@@ -83,6 +106,18 @@ func NewBreakpoints(t tracer) *Breakpoints {
 	return &Breakpoints{t: t, bps: make(map[uint64]*Breakpoint)}
 }
 
+// breakpointMask is the byte mask of the breakpoint instruction inside a
+// peeked word: the low len(breakpointInsn) bytes, because every supported
+// architecture is little-endian and patches the instruction at the lowest
+// address of the word.
+func breakpointMask() uint64 {
+	var mask uint64
+	for range breakpointInsn {
+		mask = (mask << 8) | 0xFF
+	}
+	return mask
+}
+
 // Set installs a breakpoint at addr (replaces any existing one).
 func (bm *Breakpoints) Set(addr uint64, label string) (*Breakpoint, error) {
 	return bm.SetWithCond(addr, label, nil)
@@ -100,13 +135,12 @@ func (bm *Breakpoints) SetWithCond(addr uint64, label string, cond *Condition) (
 	if err != nil {
 		return nil, err
 	}
-	orig := byte(word)
-	// Patch with the breakpoint instruction, preserving the rest of the word.
-	mask := uint64(0)
-	for range breakpointInsn {
-		mask = (mask << 8) | 0xFF
+	orig := make([]byte, len(breakpointInsn))
+	for i := range orig {
+		orig[i] = byte(word >> (8 * i))
 	}
-	patched := (word &^ mask) | breakpointWord(breakpointInsn)
+	// Patch with the breakpoint instruction, preserving the rest of the word.
+	patched := (word &^ breakpointMask()) | breakpointWord(breakpointInsn)
 	if err := bm.t.Poke(addr, patched); err != nil {
 		return nil, err
 	}
@@ -134,26 +168,40 @@ func (bm *Breakpoints) Info() string {
 		}
 		cond := ""
 		if bp.Cond != nil {
-			cond = fmt.Sprintf(" if %s %s %#x", bp.Cond.Reg, bp.Cond.Op, bp.Cond.Value)
+			cond = " if " + bp.Cond.String()
 		}
 		result.WriteString(fmt.Sprintf("  %d: %s at %#x [%s, %d hits]%s\n", i, label, bp.Addr, status, bp.hits, cond))
 	}
 	return result.String()
 }
 
-// Clear removes the breakpoint at addr, restoring the original byte.
+// restore writes the saved original bytes back over the breakpoint
+// instruction, preserving the rest of the peeked word.  It reports whether
+// both the peek and the poke succeeded.
+func (bm *Breakpoints) restore(addr uint64, bp *Breakpoint) bool {
+	word, err := bm.t.Peek(addr)
+	if err != nil {
+		return false
+	}
+	orig := uint64(0)
+	for i, b := range bp.Orig {
+		orig |= uint64(b) << (8 * i)
+	}
+	return bm.t.Poke(addr, (word&^breakpointMask())|orig) == nil
+}
+
+// Clear removes the breakpoint at addr, restoring the original bytes.
 func (bm *Breakpoints) Clear(addr uint64) error {
 	bp, ok := bm.bps[addr]
 	if !ok {
 		return fmt.Errorf("debug: no breakpoint at %#x", addr)
 	}
-	word, err := bm.t.Peek(addr)
-	if err != nil {
-		return err
-	}
-	restored := (word &^ 0xFF) | uint64(bp.Orig)
-	if err := bm.t.Poke(addr, restored); err != nil {
-		return err
+	if !bm.restore(addr, bp) {
+		word, err := bm.t.Peek(addr)
+		if err != nil {
+			return err
+		}
+		return fmt.Errorf("debug: restore breakpoint at %#x failed, word is %#x", addr, word)
 	}
 	delete(bm.bps, addr)
 	return nil
@@ -185,43 +233,54 @@ func (bm *Breakpoints) All() []*Breakpoint {
 
 // HandleTrap is called after the debuggee stops on SIGTRAP.  It checks
 // whether the trap was caused by one of our breakpoints (PC-adjust matches
-// a breakpoint address), restores the original byte, rewinds PC, and
+// a breakpoint address), restores the original bytes, rewinds PC, and
 // returns the breakpoint that was hit (or nil if it was a single-step).
 // Hits returns how many times the breakpoint has been hit.
 func (bp *Breakpoint) Hits() int { return bp.hits }
 
 func (bm *Breakpoints) HandleTrap(regs *Regs) *Breakpoint {
-	// After a breakpoint trap, PC points past the breakpoint instruction.
+	// On amd64 the kernel reports the trap with RIP past the INT3; on the
+	// other supported architectures the PC still stands on the trap
+	// instruction, which breakpointPCAdjust encodes per architecture.
 	trapAddr := regs.GetPC() - uint64(breakpointPCAdjust)
 	bp, ok := bm.bps[trapAddr]
 	if !ok || !bp.Enabled {
 		return nil // single-step trap or unknown
 	}
 	// Check the condition (if any).
-	if bp.Cond != nil && !bp.Cond.Eval(regs) {
-		// Condition not met, restore the byte but do NOT rewind RIP.
-		// The process continues from the next instruction (past the INT3).
-		word, err := bm.t.Peek(trapAddr)
-		if err == nil {
-			restored := (word &^ 0xFF) | uint64(bp.Orig)
-			bm.t.Poke(trapAddr, restored)
+	if bp.Cond != nil && !bp.Cond.Eval(regs, bm.peekValue) {
+		// Condition not met: step the original instruction and re-arm the
+		// breakpoint, leaving the debuggee stopped just past it, ready to
+		// resume silently.  The PC must be rewound first: on architectures
+		// that report the trap past the instruction (amd64) it would
+		// otherwise sit on the second byte of the replaced instruction.
+		if !bm.restore(trapAddr, bp) {
+			return nil
 		}
-		// RIP is already past the INT3 (trapAddr + 1). Don't rewind.
+		regs.SetPC(trapAddr)
+		if err := bm.t.SetRegs(regs); err != nil {
+			return nil
+		}
+		if err := bm.t.Step(); err != nil {
+			return nil
+		}
+		bm.Reinsert(trapAddr)
 		return nil
 	}
 	bp.hits++
-	// Restore the original byte.
-	word, err := bm.t.Peek(trapAddr)
-	if err == nil {
-		restored := (word &^ 0xFF) | uint64(bp.Orig)
-		bm.t.Poke(trapAddr, restored)
-	}
-	// Rewind PC to re-execute the original instruction.
+	// Restore the original bytes and rewind PC to re-execute them.
+	bm.restore(trapAddr, bp)
 	regs.SetPC(trapAddr)
 	bm.t.SetRegs(regs)
 	return bp
 }
 
+// peekValue adapts tracer.Peek to the Condition value reader.
+func (bm *Breakpoints) peekValue(addr uint64) (uint64, bool) {
+	v, err := bm.t.Peek(addr)
+	return v, err == nil
+}
+
 // Reinsert re-inserts the breakpoint at addr after a single-step past it.
 // Called after Step() when we want the breakpoint to fire again on the
 // next Continue().
@@ -234,11 +293,7 @@ func (bm *Breakpoints) Reinsert(addr uint64) error {
 	if err != nil {
 		return err
 	}
-	mask := uint64(0)
-	for range breakpointInsn {
-		mask = (mask << 8) | 0xFF
-	}
-	patched := (word &^ mask) | breakpointWord(breakpointInsn)
+	patched := (word &^ breakpointMask()) | breakpointWord(breakpointInsn)
 	return bm.t.Poke(addr, patched)
 }
 

debug/debug_arch_test.go

@@ -0,0 +1,265 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+//go:build linux
+
+package debug
+
+// Architecture-neutral tests: label and line tables, and the breakpoint
+// manager against the mock tracer.  These do not launch a debuggee, so they
+// build on every supported linux architecture.
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestLineAt(t *testing.T) {
+	lines := []SourceLine{
+		{Offset: 0, Line: 5},
+		{Offset: 5, Line: 6},
+		{Offset: 10, Line: 7},
+		{Offset: 15, Line: 8},
+	}
+
+	tests := []struct {
+		offset int
+		want   int
+	}{
+		{0, 5},
+		{1, 5},
+		{4, 5},
+		{5, 6},
+		{7, 6},
+		{10, 7},
+		{12, 7},
+		{15, 8},
+		{20, 8},
+	}
+
+	for _, tt := range tests {
+		got := lineAt(lines, tt.offset)
+		if got != tt.want {
+			t.Errorf("lineAt(lines, %d) = %d, want %d", tt.offset, got, tt.want)
+		}
+	}
+
+	// Empty table.
+	if lineAt(nil, 5) != 0 {
+		t.Error("lineAt(nil, 5) should return 0")
+	}
+}
+
+func TestOffsetForLine(t *testing.T) {
+	lines := []SourceLine{
+		{Offset: 0, Line: 5},
+		{Offset: 5, Line: 6},
+		{Offset: 10, Line: 7},
+	}
+
+	tests := []struct {
+		line int
+		want int
+	}{
+		{5, 0},
+		{6, 5},
+		{7, 10},
+		{99, -1}, // not found
+		{0, -1},  // not found
+	}
+
+	for _, tt := range tests {
+		got := offsetForLine(lines, tt.line)
+		if got != tt.want {
+			t.Errorf("offsetForLine(lines, %d) = %d, want %d", tt.line, got, tt.want)
+		}
+	}
+}
+
+func TestNearestLabel(t *testing.T) {
+	labels := []Label{
+		{Name: "start", Offset: 0},
+		{Name: "loop", Offset: 10},
+		{Name: "done", Offset: 20},
+	}
+
+	tests := []struct {
+		offset int
+		want   string
+	}{
+		{0, "start"},
+		{5, "start"},
+		{10, "loop"},
+		{15, "loop"},
+		{20, "done"},
+		{25, "done"},
+	}
+
+	for _, tt := range tests {
+		got := nearestLabel(labels, tt.offset)
+		if got != tt.want {
+			t.Errorf("nearestLabel(labels, %d) = %q, want %q", tt.offset, got, tt.want)
+		}
+	}
+}
+
+func TestBreakpointsSetAndClear(t *testing.T) {
+	tr := newMockTracer()
+	bm := NewBreakpoints(tr)
+
+	// Set a breakpoint at address 0x1000.
+	bp, err := bm.Set(0x1000, "test")
+	if err != nil {
+		t.Fatalf("Set: %v", err)
+	}
+	if !bp.Enabled {
+		t.Error("breakpoint not enabled")
+	}
+	if bp.Label != "test" {
+		t.Errorf("label = %q, want test", bp.Label)
+	}
+
+	// Verify Peek was called.
+	if len(tr.peeks) != 1 || tr.peeks[0] != 0x1000 {
+		t.Errorf("peeks = %v, want [0x1000]", tr.peeks)
+	}
+
+	// Verify Poke wrote the breakpoint instruction's bytes.
+	if len(tr.pokes) != 1 || tr.pokes[0].addr != 0x1000 {
+		t.Errorf("pokes = %v", tr.pokes)
+	}
+	if got := tr.pokes[0].val & breakpointMask(); got != breakpointWord(breakpointInsn) {
+		t.Errorf("patched bytes %#x, want %#x", got, breakpointWord(breakpointInsn))
+	}
+
+	// At should find it.
+	if bm.At(0x1000) == nil {
+		t.Error("At(0x1000) returned nil")
+	}
+
+	// All should return it.
+	all := bm.All()
+	if len(all) != 1 {
+		t.Errorf("All() = %d breakpoints, want 1", len(all))
+	}
+
+	// Clear it.
+	if err := bm.Clear(0x1000); err != nil {
+		t.Fatalf("Clear: %v", err)
+	}
+	if bm.At(0x1000) != nil {
+		t.Error("At(0x1000) after Clear should be nil")
+	}
+}
+
+// TestBreakpointRestoreWidth proves the restore path writes back every
+// byte of the breakpoint instruction's width, not just the first byte: on
+// arm64, riscv64 and loong64 the instruction is four bytes, and restoring
+// one byte would leave three bytes of the trap instruction in place.
+func TestBreakpointRestoreWidth(t *testing.T) {
+	tr := newMockTracer()
+	bm := NewBreakpoints(tr)
+	tr.mem[0x3000] = 0x11
+	tr.mem[0x3001] = 0x22
+	tr.mem[0x3002] = 0x33
+	tr.mem[0x3003] = 0x44
+
+	if _, err := bm.Set(0x3000, "width"); err != nil {
+		t.Fatalf("Set: %v", err)
+	}
+	for i, b := range breakpointInsn {
+		if tr.mem[0x3000+uint64(i)] != b {
+			t.Fatalf("byte %d after Set = %#x, want the breakpoint byte %#x", i, tr.mem[0x3000+uint64(i)], b)
+		}
+	}
+	if len(bm.At(0x3000).Orig) != len(breakpointInsn) {
+		t.Fatalf("Orig holds %d bytes, want %d", len(bm.At(0x3000).Orig), len(breakpointInsn))
+	}
+
+	if err := bm.Clear(0x3000); err != nil {
+		t.Fatalf("Clear: %v", err)
+	}
+	want := []byte{0x11, 0x22, 0x33, 0x44}
+	for i, b := range want {
+		if tr.mem[0x3000+uint64(i)] != b {
+			t.Errorf("byte %d after Clear = %#x, want %#x (restore must cover the full instruction width)", i, tr.mem[0x3000+uint64(i)], b)
+		}
+	}
+}
+
+func TestBreakpointsSetWithCond(t *testing.T) {
+	tr := newMockTracer()
+	bm := NewBreakpoints(tr)
+
+	cond := &Condition{Reg: "rax", Op: "==", Value: 42}
+	bp, err := bm.SetWithCond(0x2000, "cond_test", cond)
+	if err != nil {
+		t.Fatalf("SetWithCond: %v", err)
+	}
+	if bp.Cond == nil || bp.Cond.Value != 42 {
+		t.Error("condition not set")
+	}
+
+	// Re-setting the same address should update the condition.
+	cond2 := &Condition{Reg: "rbx", Op: "<", Value: 100}
+	bp2, err := bm.SetWithCond(0x2000, "cond_test2", cond2)
+	if err != nil {
+		t.Fatalf("SetWithCond (update): %v", err)
+	}
+	if bp2.Cond.Value != 100 {
+		t.Error("condition not updated")
+	}
+	// Should have only 1 Peek (first Set), second is update (no Peek needed).
+	if len(tr.peeks) != 1 {
+		t.Errorf("expected 1 Peek, got %d", len(tr.peeks))
+	}
+}
+
+func TestBreakpointsClearAll(t *testing.T) {
+	tr := newMockTracer()
+	bm := NewBreakpoints(tr)
+
+	bm.Set(0x1000, "a")
+	bm.Set(0x2000, "b")
+	bm.Set(0x3000, "c")
+
+	if len(bm.All()) != 3 {
+		t.Fatalf("expected 3 breakpoints, got %d", len(bm.All()))
+	}
+
+	bm.ClearAll()
+	if len(bm.All()) != 0 {
+		t.Errorf("ClearAll: expected 0 breakpoints, got %d", len(bm.All()))
+	}
+}
+
+func TestBreakpointInfo(t *testing.T) {
+	tr := newMockTracer()
+	bm := NewBreakpoints(tr)
+	bm.Set(0x4000, "info_test")
+
+	info := bm.Info()
+	if info == "" {
+		t.Error("Info returned empty string")
+	}
+	if !strings.Contains(info, "info_test") {
+		t.Errorf("Info %q does not contain label", info)
+	}
+}
+
+// TestConditionString covers the display of all three condition forms.
+func TestConditionString(t *testing.T) {
+	tests := []struct {
+		cond Condition
+		want string
+	}{
+		{Condition{Reg: "rax", Op: "==", Value: 42}, "rax == 0x2a"},
+		{Condition{Reg: "rax", Op: "!=", Reg2: "rbx"}, "rax != rbx"},
+		{Condition{Reg: "rax", Op: "<", MemAddr: 0x5000}, "rax < *0x5000"},
+	}
+	for _, tt := range tests {
+		if got := tt.cond.String(); got != tt.want {
+			t.Errorf("Condition.String() = %q, want %q", got, tt.want)
+		}
+	}
+}

debug/debug_test.go

@@ -6,7 +6,6 @@
 package debug
 
 import (
-	"strings"
 	"testing"
 )
 
@@ -48,7 +47,7 @@ func TestConditionEval(t *testing.T) {
 	}
 
 	for _, tt := range tests {
-		got := tt.cond.Eval(regs)
+		got := tt.cond.Eval(regs, nil)
 		if got != tt.want {
 			t.Errorf("Condition{%q %q %d}.Eval() = %v, want %v",
 				tt.cond.Reg, tt.cond.Op, tt.cond.Value, got, tt.want)
@@ -56,65 +55,33 @@ func TestConditionEval(t *testing.T) {
 	}
 }
 
-func TestLineAt(t *testing.T) {
-	lines := []SourceLine{
-		{Offset: 0, Line: 5},
-		{Offset: 5, Line: 6},
-		{Offset: 10, Line: 7},
-		{Offset: 15, Line: 8},
-	}
-
-	tests := []struct {
-		offset int
-		want   int
-	}{
-		{0, 5},
-		{1, 5},
-		{4, 5},
-		{5, 6},
-		{7, 6},
-		{10, 7},
-		{12, 7},
-		{15, 8},
-		{20, 8},
-	}
-
-	for _, tt := range tests {
-		got := lineAt(lines, tt.offset)
-		if got != tt.want {
-			t.Errorf("lineAt(lines, %d) = %d, want %d", tt.offset, got, tt.want)
+// TestConditionEvalMem covers the register-memory form: the value is read
+// through the supplied reader, and a missing or failing reader must not
+// block the breakpoint.
+func TestConditionEvalMem(t *testing.T) {
+	regs := &Regs{RAX: 7}
+	mem := func(addr uint64) (uint64, bool) {
+		if addr == 0x5000 {
+			return 7, true
 		}
+		return 0, false
 	}
 
-	// Empty table.
-	if lineAt(nil, 5) != 0 {
-		t.Error("lineAt(nil, 5) should return 0")
+	eq := Condition{Reg: "rax", Op: "==", MemAddr: 0x5000}
+	if !eq.Eval(regs, mem) {
+		t.Error("register-memory comparison with matching word should hold")
 	}
-}
-
-func TestOffsetForLine(t *testing.T) {
-	lines := []SourceLine{
-		{Offset: 0, Line: 5},
-		{Offset: 5, Line: 6},
-		{Offset: 10, Line: 7},
+	ne := Condition{Reg: "rax", Op: "!=", MemAddr: 0x5000}
+	if ne.Eval(regs, mem) {
+		t.Error("register-memory comparison with mismatching word should not hold")
 	}
-
-	tests := []struct {
-		line int
-		want int
-	}{
-		{5, 0},
-		{6, 5},
-		{7, 10},
-		{99, -1}, // not found
-		{0, -1},  // not found
+	bad := Condition{Reg: "rax", Op: "==", MemAddr: 0x6000}
+	if !bad.Eval(regs, mem) {
+		t.Error("unreadable memory must not block the breakpoint")
 	}
-
-	for _, tt := range tests {
-		got := offsetForLine(lines, tt.line)
-		if got != tt.want {
-			t.Errorf("offsetForLine(lines, %d) = %d, want %d", tt.line, got, tt.want)
-		}
+	noReader := Condition{Reg: "rax", Op: "==", MemAddr: 0x5000}
+	if !noReader.Eval(regs, nil) {
+		t.Error("missing memory reader must not block the breakpoint")
 	}
 }
 
@@ -141,139 +108,6 @@ func TestDecodeRflags(t *testing.T) {
 	}
 }
 
-func TestNearestLabel(t *testing.T) {
-	labels := []Label{
-		{Name: "start", Offset: 0},
-		{Name: "loop", Offset: 10},
-		{Name: "done", Offset: 20},
-	}
-
-	tests := []struct {
-		offset int
-		want   string
-	}{
-		{0, "start"},
-		{5, "start"},
-		{10, "loop"},
-		{15, "loop"},
-		{20, "done"},
-		{25, "done"},
-	}
-
-	for _, tt := range tests {
-		got := nearestLabel(labels, tt.offset)
-		if got != tt.want {
-			t.Errorf("nearestLabel(labels, %d) = %q, want %q", tt.offset, got, tt.want)
-		}
-	}
-}
-
-func TestBreakpointsSetAndClear(t *testing.T) {
-	tr := newMockTracer()
-	bm := NewBreakpoints(tr)
-
-	// Set a breakpoint at address 0x1000.
-	bp, err := bm.Set(0x1000, "test")
-	if err != nil {
-		t.Fatalf("Set: %v", err)
-	}
-	if !bp.Enabled {
-		t.Error("breakpoint not enabled")
-	}
-	if bp.Label != "test" {
-		t.Errorf("label = %q, want test", bp.Label)
-	}
-
-	// Verify Peek was called.
-	if len(tr.peeks) != 1 || tr.peeks[0] != 0x1000 {
-		t.Errorf("peeks = %v, want [0x1000]", tr.peeks)
-	}
-
-	// Verify Poke wrote INT3.
-	if len(tr.pokes) != 1 || tr.pokes[0].addr != 0x1000 {
-		t.Errorf("pokes = %v", tr.pokes)
-	}
-
-	// At should find it.
-	if bm.At(0x1000) == nil {
-		t.Error("At(0x1000) returned nil")
-	}
-
-	// All should return it.
-	all := bm.All()
-	if len(all) != 1 {
-		t.Errorf("All() = %d breakpoints, want 1", len(all))
-	}
-
-	// Clear it.
-	if err := bm.Clear(0x1000); err != nil {
-		t.Fatalf("Clear: %v", err)
-	}
-	if bm.At(0x1000) != nil {
-		t.Error("At(0x1000) after Clear should be nil")
-	}
-}
-
-func TestBreakpointsSetWithCond(t *testing.T) {
-	tr := newMockTracer()
-	bm := NewBreakpoints(tr)
-
-	cond := &Condition{Reg: "rax", Op: "==", Value: 42}
-	bp, err := bm.SetWithCond(0x2000, "cond_test", cond)
-	if err != nil {
-		t.Fatalf("SetWithCond: %v", err)
-	}
-	if bp.Cond == nil || bp.Cond.Value != 42 {
-		t.Error("condition not set")
-	}
-
-	// Re-setting the same address should update the condition.
-	cond2 := &Condition{Reg: "rbx", Op: "<", Value: 100}
-	bp2, err := bm.SetWithCond(0x2000, "cond_test2", cond2)
-	if err != nil {
-		t.Fatalf("SetWithCond (update): %v", err)
-	}
-	if bp2.Cond.Value != 100 {
-		t.Error("condition not updated")
-	}
-	// Should have only 1 Peek (first Set), second is update (no Peek needed).
-	if len(tr.peeks) != 1 {
-		t.Errorf("expected 1 Peek, got %d", len(tr.peeks))
-	}
-}
-
-func TestBreakpointsClearAll(t *testing.T) {
-	tr := newMockTracer()
-	bm := NewBreakpoints(tr)
-
-	bm.Set(0x1000, "a")
-	bm.Set(0x2000, "b")
-	bm.Set(0x3000, "c")
-
-	if len(bm.All()) != 3 {
-		t.Fatalf("expected 3 breakpoints, got %d", len(bm.All()))
-	}
-
-	bm.ClearAll()
-	if len(bm.All()) != 0 {
-		t.Errorf("ClearAll: expected 0 breakpoints, got %d", len(bm.All()))
-	}
-}
-
-func TestBreakpointInfo(t *testing.T) {
-	tr := newMockTracer()
-	bm := NewBreakpoints(tr)
-	bm.Set(0x4000, "info_test")
-
-	info := bm.Info()
-	if info == "" {
-		t.Error("Info returned empty string")
-	}
-	if !strings.Contains(info, "info_test") {
-		t.Errorf("Info %q does not contain label", info)
-	}
-}
-
 func TestWatchpointSlotTracking(t *testing.T) {
 	s := &Session{} // per-session slots start free
 
@@ -323,3 +157,19 @@ func TestWatchpointSlotTracking(t *testing.T) {
 		t.Errorf("FindFreeWatchpointSlot() with all slots used = %d, want -1", got)
 	}
 }
+
+// TestUnwatchSlotBound checks the bound the REPL parses against: it must
+// cover the architecture's whole slot range, not a hardcoded 0-3.
+func TestUnwatchSlotBound(t *testing.T) {
+	max := maxWatchpoints()
+	if max < 4 {
+		t.Fatalf("maxWatchpoints() = %d, want at least 4", max)
+	}
+	s := &Session{}
+	if s.IsWatchpointSlotUsed(max - 1) {
+		t.Errorf("slot %d should be free initially", max-1)
+	}
+	if s.IsWatchpointSlotUsed(max) {
+		t.Errorf("slot %d must be out of range", max)
+	}
+}

debug/disasm_linux_amd64.go

@@ -46,3 +46,11 @@ func (s *Session) DisassembleN(addr uint64, n int) string {
 	}
 	return result.String()
 }
+
+// isCallInsn reports whether disassembled text (x86asm.IntelSyntax) is a
+// call.  The first token must match exactly: a prefix test would also catch
+// unrelated mnemonics.
+func isCallInsn(text string) bool {
+	m, _, _ := strings.Cut(text, " ")
+	return strings.ToLower(m) == "call"
+}

debug/disasm_linux_arm64.go

@@ -7,6 +7,7 @@ package debug
 
 import (
 	"fmt"
+	"strings"
 
 	"sourcedock.dev/petrbalvin/gasm-devkit/arch"
 	"sourcedock.dev/petrbalvin/gasm-devkit/disasm"
@@ -44,3 +45,15 @@ func (s *Session) DisassembleN(addr uint64, n int) string {
 	}
 	return result
 }
+
+// isCallInsn reports whether disassembled text (arm64asm.GoSyntax) is a
+// call.  GoSyntax renders bl as CALL; the native mnemonic is accepted too.
+// The first token must match exactly so branches never match.
+func isCallInsn(text string) bool {
+	m, _, _ := strings.Cut(text, " ")
+	switch strings.ToLower(m) {
+	case "call", "bl":
+		return true
+	}
+	return false
+}

debug/disasm_linux_loong64.go

@@ -7,6 +7,7 @@ package debug
 
 import (
 	"fmt"
+	"strings"
 
 	"sourcedock.dev/petrbalvin/gasm-devkit/arch"
 	"sourcedock.dev/petrbalvin/gasm-devkit/disasm"
@@ -44,3 +45,16 @@ func (s *Session) DisassembleN(addr uint64, n int) string {
 	}
 	return result
 }
+
+// isCallInsn reports whether disassembled text (loong64asm.GoSyntax) is a
+// call.  GoSyntax renders bl and jirl calls as CALL (jirl returns print
+// RET); the native mnemonics are accepted too.  The first token must match
+// exactly: a "bl" prefix would catch bltz and other branches.
+func isCallInsn(text string) bool {
+	m, _, _ := strings.Cut(text, " ")
+	switch strings.ToLower(m) {
+	case "call", "bl", "jirl":
+		return true
+	}
+	return false
+}

debug/disasm_linux_riscv64.go

@@ -7,6 +7,7 @@ package debug
 
 import (
 	"fmt"
+	"strings"
 
 	"sourcedock.dev/petrbalvin/gasm-devkit/arch"
 	"sourcedock.dev/petrbalvin/gasm-devkit/disasm"
@@ -44,3 +45,17 @@ func (s *Session) DisassembleN(addr uint64, n int) string {
 	}
 	return result
 }
+
+// isCallInsn reports whether disassembled text (riscv64asm.GoSyntax) is a
+// call.  GoSyntax renders jal and jalr calls as CALL; the native mnemonics
+// are accepted too.  The first token must match exactly: a prefix test on
+// "bl" would catch branches on other architectures, and jalr as ret prints
+// RET, which must not be stepped over.
+func isCallInsn(text string) bool {
+	m, _, _ := strings.Cut(text, " ")
+	switch strings.ToLower(m) {
+	case "call", "jal", "jalr":
+		return true
+	}
+	return false
+}

debug/display_linux_amd64.go

@@ -73,9 +73,29 @@ func decodeRflags(f uint64) string {
 	return flags[:len(flags)-1]
 }
 
-// archReturnAddr reads the return address from the stack (amd64 ABI0 convention).
+// archReturnAddr reads the return address of the current frame (amd64
+// ABI0 convention).  A function that contains a CALL (or has a frame) is
+// assembled with the prologue PUSHQ BP; MOVQ SP, BP, so mid-function the
+// word at SP is the saved caller BP, a stack address, and the return
+// address sits further up.  Walk the stack from SP and take the first word
+// that lies in an executable mapping: stack and data words never do, a
+// return address always does.
 func archReturnAddr(s *Session, regs *Regs) (uint64, error) {
-	return s.Peek(regs.GetSP())
+	ranges := execRanges(s.pid)
+	for off := uint64(0); off < 512; off += 8 {
+		word, err := s.Peek(regs.RSP + off)
+		if err != nil {
+			break
+		}
+		for _, r := range ranges {
+			if word >= r.lo && word < r.hi {
+				return word, nil
+			}
+		}
+	}
+	// No mapping available or nothing code-like on the stack: fall back to
+	// the raw entry convention, [SP] before any push.
+	return s.Peek(regs.RSP)
 }
 
 // archSPLabel returns the SP register name for display.

debug/display_linux_arm64.go

@@ -5,7 +5,10 @@
 
 package debug
 
-import "fmt"
+import (
+	"encoding/binary"
+	"fmt"
+)
 
 func printRegs(regs *Regs, codeBase, funcOff uint64) {
 	fmt.Printf("  PC  = %#016x  (func+%#x)\n", regs.PC, regs.PC-codeBase-funcOff)
@@ -31,8 +34,8 @@ func printRegs(regs *Regs, codeBase, funcOff uint64) {
 func printVectorRegs(v *VectorRegs) {
 	fmt.Println("\n  Vector registers (V0-V31):")
 	for i := 0; i < 32; i += 2 {
-		fmt.Printf("  V%-2d  = %016x%016x\n", i, v.V[i][8], v.V[i][0])
-		fmt.Printf("  V%-2d  = %016x%016x\n", i+1, v.V[i+1][8], v.V[i+1][0])
+		fmt.Printf("  V%-2d  = %016x%016x\n", i, binary.LittleEndian.Uint64(v.V[i][8:16]), binary.LittleEndian.Uint64(v.V[i][0:8]))
+		fmt.Printf("  V%-2d  = %016x%016x\n", i+1, binary.LittleEndian.Uint64(v.V[i+1][8:16]), binary.LittleEndian.Uint64(v.V[i+1][0:8]))
 	}
 }
 

debug/ptrace_extra_test.go

@@ -0,0 +1,427 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+//go:build linux && amd64
+
+package debug
+
+import (
+	"bytes"
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"runtime"
+	"strings"
+	"testing"
+	"time"
+	"unsafe"
+
+	"sourcedock.dev/petrbalvin/gasm-devkit/asm"
+	"sourcedock.dev/petrbalvin/gasm-devkit/verify"
+)
+
+// Integration tests beyond the basic entry breakpoint: hardware watchpoints,
+// conditional breakpoints, next/finish over a CALL, faulting kernels and the
+// xstate vector-register readout.  All drive a real ptrace session, so they
+// run on amd64 hosts only.
+
+// writeKernel writes an assembly source to a temporary file with the
+// architecture suffix the assembler dispatcher expects.
+func writeKernel(t *testing.T, src string) string {
+	t.Helper()
+	path := filepath.Join(t.TempDir(), "kernel_amd64.s")
+	if err := os.WriteFile(path, []byte(src), 0o644); err != nil {
+		t.Fatalf("write kernel: %v", err)
+	}
+	return path
+}
+
+// launchKernel launches a session for the kernel source and returns the
+// session, its breakpoint manager and the function layout.
+func launchKernel(t *testing.T, bin, path, funcName string, args []byte) (*Session, *Breakpoints, asm.FuncLayout) {
+	t.Helper()
+	k, err := verify.Load(path)
+	if err != nil {
+		t.Fatalf("Load: %v", err)
+	}
+	t.Cleanup(k.Close)
+	fl, err := k.Func(funcName)
+	if err != nil {
+		t.Fatalf("Func: %v", err)
+	}
+	if len(args) < fl.Args {
+		padded := make([]byte, fl.Args)
+		copy(padded, args)
+		args = padded
+	}
+	sess, err := Launch(bin, path, funcName, args)
+	if err != nil {
+		t.Fatalf("Launch: %v", err)
+	}
+	t.Cleanup(sess.Kill)
+	bm := NewBreakpoints(sess)
+	return sess, bm, fl
+}
+
+// runToEntry resumes the freshly launched debuggee until the breakpoint at
+// the function entry traps, mirroring the REPL continue loop: the debuggee
+// SIGSTOPs twice (launch barrier and entry barrier) before entering the JIT
+// call.
+func runToEntry(t *testing.T, sess *Session, bm *Breakpoints, entry uint64) {
+	t.Helper()
+	for range 50 {
+		for _, bp := range bm.All() {
+			bm.Reinsert(bp.Addr)
+		}
+		if err := sess.Continue(); err != nil {
+			t.Fatalf("Continue: %v", err)
+		}
+		if sess.Exited() {
+			t.Fatal("debuggee exited before the entry breakpoint trapped")
+		}
+		regs, err := sess.GetRegs()
+		if err != nil {
+			t.Fatalf("GetRegs: %v", err)
+		}
+		if bm.HandleTrap(&regs) != nil {
+			return
+		}
+	}
+	t.Fatal("no entry breakpoint trap after 50 resumes")
+}
+
+// captureStdout runs fn with os.Stdout redirected to a pipe and returns
+// what it printed (the REPL writes its reports to stdout).
+func captureStdout(t *testing.T, fn func()) string {
+	t.Helper()
+	r, w, err := os.Pipe()
+	if err != nil {
+		t.Fatalf("pipe: %v", err)
+	}
+	old := os.Stdout
+	os.Stdout = w
+	done := make(chan string, 1)
+	go func() {
+		b, _ := io.ReadAll(r)
+		done <- string(b)
+	}()
+	defer func() { os.Stdout = old }()
+	fn()
+	w.Close()
+	return <-done
+}
+
+// TestWatchpointArmRunHit proves the debug-register offsets: the watchpoint
+// must fire on the store, with si_addr naming the watched address.  The
+// kernel writes its return value to ret+0(FP), which is the 8-byte word
+// right above the stack pointer at entry.
+func TestWatchpointArmRunHit(t *testing.T) {
+	runtime.LockOSThread()
+	defer runtime.UnlockOSThread()
+	bin := buildGasm(t)
+
+	const kernel = `#include "textflag.h"
+
+// func wpret() int64
+TEXT ·wpret(SB), NOSPLIT, $0-8
+	MOVQ $0x5a5a5a5a5a5a5a5a, AX
+	MOVQ AX, ret+0(FP)
+	RET
+`
+	path := writeKernel(t, kernel)
+	sess, bm, fl := launchKernel(t, bin, path, "wpret", nil)
+
+	entry := sess.CodeBase() + uint64(fl.Offset)
+	if _, err := bm.Set(entry, "entry"); err != nil {
+		t.Fatalf("Set: %v", err)
+	}
+	runToEntry(t, sess, bm, entry)
+
+	regs, err := sess.GetRegs()
+	if err != nil {
+		t.Fatalf("GetRegs: %v", err)
+	}
+	watched := regs.RSP + 8 // ret+0(FP): the store target
+
+	slot := sess.FindFreeWatchpointSlot()
+	if slot < 0 {
+		t.Fatal("no free watchpoint slot")
+	}
+	if err := sess.SetWatchpoint(slot, watched, WatchWrite, 8); err != nil {
+		t.Fatalf("SetWatchpoint: %v (wrong debug-register offsets?)", err)
+	}
+
+	if err := sess.Continue(); err != nil {
+		t.Fatalf("Continue: %v", err)
+	}
+	reason, addr := sess.StopInfo()
+	if reason != StopWatchpoint {
+		t.Fatalf("stop reason = %v, want StopWatchpoint (DR0-DR3/DR7 offsets are wrong)", reason)
+	}
+	if addr != watched {
+		t.Fatalf("watchpoint address = %#x, want %#x", addr, watched)
+	}
+
+	// The watched word holds the stored value: x86 data breakpoints are
+	// reported with the access complete.
+	if word, err := sess.Peek(watched); err != nil || word != 0x5a5a5a5a5a5a5a5a {
+		t.Errorf("watched word = %#x (err %v), want 0x5a5a5a5a5a5a5a5a", word, err)
+	}
+	if err := sess.ClearWatchpoint(slot); err != nil {
+		t.Fatalf("ClearWatchpoint: %v", err)
+	}
+}
+
+// TestConditionalBreakpointFalseThenTrue proves the false-condition path:
+// the breakpoint steps over the original instruction, re-arms itself and
+// keeps running silently, and the true condition stops exactly once with the
+// register in the expected state.
+func TestConditionalBreakpointFalseThenTrue(t *testing.T) {
+	runtime.LockOSThread()
+	defer runtime.UnlockOSThread()
+	bin := buildGasm(t)
+
+	const kernel = `#include "textflag.h"
+
+// func countdown(n int64) int64
+TEXT ·countdown(SB), NOSPLIT, $0-16
+	MOVQ n+0(FP), CX
+loop:
+	DECQ CX
+	CMPQ CX, $0
+	JNE loop
+	MOVQ CX, ret+8(FP)
+	RET
+`
+	path := writeKernel(t, kernel)
+	sess, bm, fl := launchKernel(t, bin, path, "countdown", []byte{8})
+
+	loopAddr := sess.CodeBase() + uint64(fl.Offset) + uint64(fl.Labels["loop"])
+	// The length of the breakpointed instruction, from a disassembly taken
+	// before the INT3 is patched in.
+	_, insnLen, err := sess.Disassemble(loopAddr)
+	if err != nil || insnLen <= 0 {
+		t.Fatalf("Disassemble at %#x: len=%d err=%v", loopAddr, insnLen, err)
+	}
+	cond := &Condition{Reg: "rcx", Op: "==", Value: 1}
+	bp, err := bm.SetWithCond(loopAddr, "loop", cond)
+	if err != nil {
+		t.Fatalf("SetWithCond: %v", err)
+	}
+
+	hits := 0
+	exited := false
+	for range 200 {
+		for _, b := range bm.All() {
+			bm.Reinsert(b.Addr)
+		}
+		if err := sess.Continue(); err != nil {
+			exited = true
+			break // the debuggee finished
+		}
+		if sess.Exited() {
+			exited = true
+			break
+		}
+		if sig := sess.LastSignal(); sig != 0 {
+			t.Fatalf("unexpected signal stop %v", sig)
+		}
+		regs, err := sess.GetRegs()
+		if err != nil {
+			t.Fatalf("GetRegs: %v", err)
+		}
+		if hit := bm.HandleTrap(&regs); hit != nil {
+			hits++
+			if regs.RCX != 1 {
+				t.Fatalf("hit with RCX=%d, want 1", regs.RCX)
+			}
+			// Park after the instruction, as the REPL does.
+			if err := sess.Step(); err != nil {
+				t.Fatalf("Step: %v", err)
+			}
+		} else {
+			// A false evaluation must leave the debuggee past the whole
+			// original instruction: a PC inside it (trapAddr+1 on amd64)
+			// means the resume happens mid-instruction.
+			fresh, err := sess.GetRegs()
+			if err != nil {
+				t.Fatalf("GetRegs: %v", err)
+			}
+			if fresh.RIP > loopAddr && fresh.RIP < loopAddr+uint64(insnLen) {
+				t.Fatalf("false evaluation left the PC at %#x, inside the %d-byte instruction at %#x",
+					fresh.RIP, insnLen, loopAddr)
+			}
+		}
+	}
+	if hits != 1 {
+		t.Fatalf("conditional breakpoint hit %d times, want exactly 1 (false evaluations must run through silently)", hits)
+	}
+	if bp.Hits() != 1 {
+		t.Errorf("bp.Hits() = %d, want 1", bp.Hits())
+	}
+	if !exited || !sess.Exited() {
+		t.Fatal("debuggee did not run to completion after the conditional hit")
+	}
+}
+
+// TestNextAndFinishOverCall proves next and finish evaluate the trap with
+// registers fetched after the stop: next lands exactly on the instruction
+// after the CALL, and finish stops exactly on the return address.
+func TestNextAndFinishOverCall(t *testing.T) {
+	runtime.LockOSThread()
+	defer runtime.UnlockOSThread()
+	bin := buildGasm(t)
+
+	const kernel = `#include "textflag.h"
+
+// func caller(x int64) int64
+// The argument travels in AX: FP argument slots of CALL-bearing functions
+// are an assembler concern outside this test's scope.
+TEXT ·caller(SB), NOSPLIT, $0-16
+	MOVQ $5, AX
+	CALL ·bump(SB)
+aftercall:
+	MOVQ AX, ret+8(FP)
+	RET
+
+// func bump(x int64) int64
+TEXT ·bump(SB), NOSPLIT, $0-0
+	ADDQ $3, AX
+	RET
+`
+	path := writeKernel(t, kernel)
+
+	// next: step the prologue and the constant load (3 instructions), then
+	// step over the CALL and check the landing address and RAX.
+	sess, bm, fl := launchKernel(t, bin, path, "caller", nil)
+	entry := sess.CodeBase() + uint64(fl.Offset)
+	if _, err := bm.Set(entry, "entry"); err != nil {
+		t.Fatalf("Set: %v", err)
+	}
+	runToEntry(t, sess, bm, entry)
+	afterOff := uint64(fl.Labels["aftercall"])
+
+	out := captureStdout(t, func() {
+		REPL(sess, bm, sess.CodeBase(), fl.Offset, fl.Size, fl.Args, nil, nil,
+			strings.NewReader("step 3\nnext\nregs\nquit\n"))
+	})
+	if !strings.Contains(out, fmt.Sprintf("func+%#x", afterOff)) {
+		t.Errorf("next did not land on the instruction after the CALL (func+%#x); output:\n%s", afterOff, out)
+	}
+	if !strings.Contains(out, "RAX = 0x0000000000000008") {
+		t.Errorf("callee did not run exactly once under next (want RAX=8); output:\n%s", out)
+	}
+
+	// finish: run to the return address read off the stack at entry.
+	sess2, bm2, fl2 := launchKernel(t, bin, path, "caller", nil)
+	entry2 := sess2.CodeBase() + uint64(fl2.Offset)
+	if _, err := bm2.Set(entry2, "entry"); err != nil {
+		t.Fatalf("Set: %v", err)
+	}
+	runToEntry(t, sess2, bm2, entry2)
+	regs, err := sess2.GetRegs()
+	if err != nil {
+		t.Fatalf("GetRegs: %v", err)
+	}
+	retAddr, err := sess2.Peek(regs.RSP)
+	if err != nil {
+		t.Fatalf("Peek return address: %v", err)
+	}
+
+	out2 := captureStdout(t, func() {
+		REPL(sess2, bm2, sess2.CodeBase(), fl2.Offset, fl2.Size, fl2.Args, nil, nil,
+			strings.NewReader("step 1\nfinish\nquit\n"))
+	})
+	want := fmt.Sprintf("finished, now at %#x\n", retAddr)
+	if !strings.Contains(out2, want) {
+		t.Errorf("finish stopped at the wrong PC; want %q in output:\n%s", want, out2)
+	}
+}
+
+// TestSignalStopSurfaced proves a faulting kernel surfaces as a reported
+// stop instead of an infinite fault loop.  A regression here hangs, so a
+// watchdog fails the run rather than letting CI stall.
+func TestSignalStopSurfaced(t *testing.T) {
+	runtime.LockOSThread()
+	defer runtime.UnlockOSThread()
+	bin := buildGasm(t)
+
+	const kernel = `#include "textflag.h"
+
+// func crash() int64
+TEXT ·crash(SB), NOSPLIT, $0-8
+	XORQ AX, AX
+	MOVQ (AX), AX
+	MOVQ AX, ret+0(FP)
+	RET
+`
+	path := writeKernel(t, kernel)
+	sess, bm, _ := launchKernel(t, bin, path, "crash", nil)
+
+	timer := time.AfterFunc(time.Minute, func() {
+		panic("watchdog: the debugger hung on the faulting kernel instead of reporting the signal stop")
+	})
+	defer timer.Stop()
+
+	out := captureStdout(t, func() {
+		REPL(sess, bm, sess.CodeBase(), 0, 0, 0, nil, nil,
+			strings.NewReader("continue\nquit\n"))
+	})
+	if !strings.Contains(out, "stopped on signal") {
+		t.Errorf("SIGSEGV did not surface as a reported stop; output:\n%s", out)
+	}
+	if !sess.Exited() {
+		t.Error("debuggee should be killed by quit after the signal stop")
+	}
+}
+
+// TestGetVectorRegsXState proves the NT_X86_XSTATE readout: the request
+// succeeds on a normal process and the XMM halves agree with
+// PTRACE_GETFPREGS.
+func TestGetVectorRegsXState(t *testing.T) {
+	// The FPRegs layout must mirror the kernel's user_fpregs_struct
+	// exactly: PTRACE_GETFPREGS fills all 512 bytes, so a short struct
+	// overflows the caller's memory.
+	if got := unsafe.Sizeof(FPRegs{}); got != 512 {
+		t.Fatalf("sizeof(FPRegs) = %d, want 512", got)
+	}
+	if got := unsafe.Offsetof(FPRegs{}.XMM); got != 160 {
+		t.Fatalf("offsetof(FPRegs.XMM) = %d, want 160", got)
+	}
+
+	runtime.LockOSThread()
+	defer runtime.UnlockOSThread()
+	bin := buildGasm(t)
+
+	const kernel = `#include "textflag.h"
+
+// func vprobe() int64
+TEXT ·vprobe(SB), NOSPLIT, $0-8
+	MOVQ $1, AX
+	MOVQ AX, ret+0(FP)
+	RET
+`
+	path := writeKernel(t, kernel)
+	sess, bm, fl := launchKernel(t, bin, path, "vprobe", nil)
+
+	entry := sess.CodeBase() + uint64(fl.Offset)
+	if _, err := bm.Set(entry, "entry"); err != nil {
+		t.Fatalf("Set: %v", err)
+	}
+	runToEntry(t, sess, bm, entry)
+
+	v, err := sess.GetVectorRegs()
+	if err != nil {
+		t.Fatalf("GetVectorRegs: %v", err)
+	}
+	fp, err := sess.GetFPRegs()
+	if err != nil {
+		t.Fatalf("GetFPRegs: %v", err)
+	}
+	for i := range 16 {
+		if !bytes.Equal(v.YMM[i][:16], fp.XMM[i][:]) {
+			t.Errorf("YMM%d low half %x, want the FPRegs XMM half %x", i, v.YMM[i][:16], fp.XMM[i][:])
+		}
+	}
+}

debug/ptrace_linux.go

@@ -23,7 +23,13 @@ type Session struct {
 	stopped  bool
 	exited   bool
 	codeBase uint64   // base address of the JIT code in the debuggee
-	wpSlots  [16]bool // hardware watchpoint slots in use (DR0-DR3, arm64 BADVR0-15)
+	tmpDir   string   // scratch directory of the session, removed on Kill
+	wpSlots  [16]bool // hardware watchpoint slots in use (DR0-DR3, arm64 DBGWVR0-15)
+	// lastSignal holds the signal of the most recent stop when that stop
+	// was a genuine signal-delivery-stop the caller must see (a fault such
+	// as SIGSEGV, SIGBUS, SIGFPE or SIGILL); 0 for breakpoint traps,
+	// single-steps, SIGSTOP and suppressed runtime signals.
+	lastSignal syscall.Signal
 }
 
 // Launch starts the debuggee subprocess (gasm debug --target ...) and
@@ -78,7 +84,7 @@ func LaunchWithBuffers(gasmBin, asmPath, funcName string, args []byte, bufSpec s
 		return nil, nil, fmt.Errorf("debug: start debuggee: %w", err)
 	}
 
-	s := &Session{pid: cmd.Process.Pid, cmd: cmd}
+	s := &Session{pid: cmd.Process.Pid, cmd: cmd, tmpDir: tmpDir}
 
 	readyFile := filepath.Join(tmpDir, "ready")
 	for range 500 {
@@ -125,29 +131,17 @@ func LaunchWithBuffers(gasmBin, asmPath, funcName string, args []byte, bufSpec s
 	return s, bufAddrs, nil
 }
 
-// wait waits for the debuggee to stop and returns the wait status.
-func (s *Session) wait() error {
-	var ws syscall.WaitStatus
-	_, err := syscall.Wait4(s.pid, &ws, 0, nil)
-	if err != nil {
-		return err
-	}
-	if ws.Exited() {
-		s.exited = true
-		return fmt.Errorf("debuggee exited with status %d", ws.ExitStatus())
-	}
-	s.stopped = true
-	return nil
-}
-
 // waitStopped consumes ptrace-stop events until one the debugger cares
-// about arrives: SIGTRAP (a breakpoint or a completed single-step) or the
-// debuggee's own SIGSTOP.  A Go tracee's runtime raises SIGURG for
-// asynchronous preemption, and every signal on a traced thread surfaces as
-// a signal-delivery-stop, so those are suppressed and the tracee resumed
-// without them.  Runtime noise is why a single wait can return in the
-// middle of runtime code and a resume can then fail: the event stream must
-// be drained by the tracer.
+// about arrives: SIGTRAP (a breakpoint or a completed single-step), the
+// debuggee's own SIGSTOP, or a genuine signal-delivery-stop.  A Go tracee's
+// runtime raises SIGURG for asynchronous preemption, and every signal on a
+// traced thread surfaces as a signal-delivery-stop, so SIGURG is suppressed
+// and the tracee resumed without it.  Every other signal (SIGSEGV, SIGBUS,
+// SIGFPE, SIGILL, ...) is returned to the caller: resuming with signal 0
+// would restart the faulting instruction and fault forever, so a faulting
+// kernel must surface as a stop the caller reports.  Runtime noise is also
+// why a single wait can return in the middle of runtime code and a resume
+// can then fail: the event stream must be drained by the tracer.
 func (s *Session) waitStopped() (syscall.Signal, error) {
 	for {
 		var ws syscall.WaitStatus
@@ -165,10 +159,12 @@ func (s *Session) waitStopped() (syscall.Signal, error) {
 		switch sig := ws.StopSignal(); sig {
 		case syscall.SIGTRAP, syscall.SIGSTOP:
 			s.stopped = true
+			s.lastSignal = 0
 			return sig, nil
-		default:
-			// Runtime noise (SIGURG preemption and friends): resume the
-			// tracee without delivering the signal.
+		case syscall.SIGURG:
+			// Go runtime asynchronous preemption: resume the tracee
+			// without delivering the signal.
+			s.lastSignal = 0
 			if _, _, errno := syscall.Syscall6(
 				syscall.SYS_PTRACE,
 				uintptr(syscall.PTRACE_CONT),
@@ -177,10 +173,22 @@ func (s *Session) waitStopped() (syscall.Signal, error) {
 			); errno != 0 {
 				return 0, fmt.Errorf("debug: PTRACE_CONT: %w", errno)
 			}
+		default:
+			// A genuine signal-delivery-stop.  Report it; the caller
+			// decides how to proceed.
+			s.stopped = true
+			s.lastSignal = sig
+			return sig, nil
 		}
 	}
 }
 
+// LastSignal returns the signal of the most recent stop when that stop was
+// a genuine signal-delivery-stop (a fault such as SIGSEGV, SIGFPE, SIGILL
+// or SIGBUS), and 0 for breakpoint traps, single-steps, SIGSTOP and
+// suppressed runtime signals.
+func (s *Session) LastSignal() syscall.Signal { return s.lastSignal }
+
 // Peek reads a word (8 bytes) from the debuggee's memory at addr.
 func (s *Session) Peek(addr uint64) (uint64, error) {
 	mem, err := os.OpenFile(fmt.Sprintf("/proc/%d/mem", s.pid), os.O_RDONLY, 0)
@@ -294,7 +302,8 @@ func (s *Session) Pid() int { return s.pid }
 // CodeBase returns the base address of the JIT code in the debuggee.
 func (s *Session) CodeBase() uint64 { return s.codeBase }
 
-// Kill terminates the debuggee.
+// Kill terminates the debuggee and removes the session's scratch
+// directory, so a successful session leaves no gasm-debug-* debris behind.
 func (s *Session) Kill() {
 	if !s.exited {
 		syscall.Kill(s.pid, syscall.SIGKILL)
@@ -304,6 +313,35 @@ func (s *Session) Kill() {
 	if s.cmd != nil && s.cmd.Process != nil {
 		s.cmd.Wait()
 	}
+	if s.tmpDir != "" {
+		os.RemoveAll(s.tmpDir)
+		s.tmpDir = ""
+	}
+}
+
+// execRange is one executable mapping of the debuggee.
+type execRange struct {
+	lo, hi uint64
+}
+
+// execRanges parses the debuggee's executable mappings from /proc/pid/maps.
+func execRanges(pid int) []execRange {
+	data, err := os.ReadFile(fmt.Sprintf("/proc/%d/maps", pid))
+	if err != nil {
+		return nil
+	}
+	var out []execRange
+	for line := range strings.SplitSeq(string(data), "\n") {
+		fields := strings.Fields(line)
+		if len(fields) < 2 || !strings.Contains(fields[1], "x") {
+			continue
+		}
+		var lo, hi uint64
+		if _, err := fmt.Sscanf(fields[0], "%x-%x", &lo, &hi); err == nil {
+			out = append(out, execRange{lo, hi})
+		}
+	}
+	return out
 }
 
 // findRWXMapping reads /proc/pid/maps and returns the base address of the

debug/ptrace_linux_amd64.go

@@ -6,6 +6,7 @@
 package debug
 
 import (
+	"encoding/binary"
 	"fmt"
 	"syscall"
 	"unsafe"
@@ -44,20 +45,24 @@ func (s *Session) SetRegs(regs *Regs) error {
 	return nil
 }
 
-// FPRegs holds the x87 FPU and SSE (XMM) register state from PTRACE_GETFPREGS.
+// FPRegs holds the x87 FPU and SSE (XMM) register state from
+// PTRACE_GETFPREGS.  The layout is the kernel's struct user_fpregs_struct
+// (sys/user.h), the FXSAVE image: 512 bytes with XMM0-15 at offset 160.
+// The i387 fcs/ds segment fields do not exist in the 64-bit layout.  The
+// size matters: the copy fills all 512 bytes, so a short or misaligned
+// struct makes PTRACE_GETFPREGS overflow the caller's memory.
 type FPRegs struct {
 	FCW       uint16
 	FSW       uint16
-	FTW       byte
+	FTW       uint16
 	FOP       uint16
 	FIP       uint64
-	FCS       uint16
 	FDP       uint64
-	FDS       uint16
 	MXCSR     uint32
 	MXCSRMask uint32
 	ST        [8][16]byte  // x87 stack (10 bytes per reg, padded to 16)
-	XMM       [16][16]byte // XMM0-15
+	XMM       [16][16]byte // XMM0-15, struct offset 160
+	Reserved  [96]byte     // FXSAVE padding, to the full 512 bytes
 }
 
 // GetFPRegs retrieves the FPU/SSE register state of the stopped debuggee.
@@ -82,16 +87,68 @@ type VectorRegs struct {
 	YMM [16][32]byte // YMM0-15 (full 256-bit values)
 }
 
-// GetVectorRegs retrieves the YMM registers via PTRACE_GETREGSET + XSAVE.
+// NT_X86_XSTATE (0x202), the xsave extended-state regset
+// (include/uapi/linux/elf.h).
+const ntX86XState = 0x202
+
+// Layout of the buffer PTRACE_GETREGSET returns for NT_X86_XSTATE: the
+// 512-byte legacy fxsave image (x87 state in 0-159, XMM0-15 in 160-511),
+// then the 64-byte xsave header whose first 8 bytes are xstate_bv, then one
+// component per set feature bit, each 64-byte aligned.  The YMM high halves
+// are the first extended component, at offset 576; that offset is fixed by
+// the ISA on AVX-capable x86-64.  XFEATURE_MASK_YMM is bit 2 of xstate_bv
+// (arch/x86/include/asm/fpu/types.h); the high halves are zero when the bit
+// is clear.
+const (
+	xsaveXMMOffset    = 160
+	xsaveXMMSize      = 256
+	xsaveHeaderOffset = 512
+	xsaveBVOffset     = xsaveHeaderOffset
+	ymmOffset         = xsaveHeaderOffset + 64 // 576
+	ymmSize           = 256                    // 16 registers, 16 bytes each
+	xfeatureMaskYMM   = 1 << 2
+	xstateMaxBuffer   = 4096 // CPUID(0xD).xsave_size is far below this
+)
+
+// GetVectorRegs retrieves the YMM registers via PTRACE_GETREGSET on
+// NT_X86_XSTATE.  The low (XMM) halves always come from the legacy image;
+// the high halves are copied only when xstate_bv reports the YMM feature,
+// and read as zero otherwise.  When the regset request fails the FP image
+// still provides correct XMM halves, so that is the fallback.
 func (s *Session) GetVectorRegs() (VectorRegs, error) {
 	var v VectorRegs
-	fp, err := s.GetFPRegs()
-	if err != nil {
-		return v, err
+	buf := make([]byte, xstateMaxBuffer)
+	iovec := syscall.Iovec{
+		Base: &buf[0],
+		Len:  uint64(len(buf)),
 	}
+	_, _, errno := syscall.Syscall6(
+		syscall.SYS_PTRACE,
+		uintptr(syscall.PTRACE_GETREGSET),
+		uintptr(s.pid),
+		uintptr(ntX86XState),
+		uintptr(unsafe.Pointer(&iovec)),
+		0, 0,
+	)
+	if errno != 0 {
+		fp, err := s.GetFPRegs()
+		if err != nil {
+			return v, err
+		}
+		for i := range 16 {
+			copy(v.YMM[i][:16], fp.XMM[i][:])
+		}
+		return v, nil
+	}
+	n := int(iovec.Len)
 	for i := range 16 {
-		for j := range 16 {
-			v.YMM[i][j] = fp.XMM[i][j]
+		copy(v.YMM[i][:16], buf[xsaveXMMOffset+16*i:xsaveXMMOffset+16*i+16])
+	}
+	if n >= ymmOffset+ymmSize {
+		if binary.LittleEndian.Uint64(buf[xsaveBVOffset:xsaveBVOffset+8])&xfeatureMaskYMM != 0 {
+			for i := range 16 {
+				copy(v.YMM[i][16:], buf[ymmOffset+16*i:ymmOffset+16*i+16])
+			}
 		}
 	}
 	return v, nil

debug/regs_linux_amd64.go

@@ -91,5 +91,9 @@ func (r *Regs) RegValue(name string) (uint64, bool) {
 // breakpointInsn is the software breakpoint instruction.
 var breakpointInsn = []byte{0xCC} // INT3
 
-// breakpointPCAdjust is how far PC is past the breakpoint instruction after a trap.
+// breakpointPCAdjust is how far PC is past the breakpoint instruction after
+// a trap.  x86-64 reports the #DB for INT3 with RIP on the byte after the
+// INT3 (Intel SDM vol 3, "Debug Exceptions"), so the trap address is
+// PC-1.  The other supported architectures leave the PC on the trap
+// instruction and use 0 there.
 const breakpointPCAdjust = 1

debug/regs_linux_arm64.go

@@ -130,5 +130,11 @@ func (r *Regs) RegValue(name string) (uint64, bool) {
 // breakpointInsn is the software breakpoint instruction (BRK #0).
 var breakpointInsn = []byte{0x00, 0x00, 0x20, 0xD4} // BRK #0
 
-// breakpointPCAdjust is how far PC is past the breakpoint instruction after a trap.
-const breakpointPCAdjust = 4
+// breakpointPCAdjust is how far PC is past the breakpoint instruction after
+// a trap: 0, because the arm64 kernel delivers the BRK SIGTRAP with the PC
+// still on the BRK.  do_el0_brk64 calls send_user_sigtrap, which uses
+// instruction_pointer(regs) unmodified (arch/arm64/kernel/debug-monitors.c);
+// only the kernel-internal skip paths advance the PC.  GDB history agrees:
+// decr_pc_after_break on aarch64 Linux is 0 (the +4 variant was a QEMU bug,
+// sourceware PR 17280).
+const breakpointPCAdjust = 0

debug/regs_linux_loong64.go

@@ -126,5 +126,9 @@ func (r *Regs) RegValue(name string) (uint64, bool) {
 // breakpointInsn is the software breakpoint instruction (BRK $0).
 var breakpointInsn = []byte{0x05, 0x00, 0x2a, 0x00} // break 0
 
-// breakpointPCAdjust is how far PC is past the breakpoint instruction after a trap.
-const breakpointPCAdjust = 4
+// breakpointPCAdjust is how far PC is past the breakpoint instruction after
+// a trap: 0, because the kernel delivers the break SIGTRAP with csr_era
+// still on the break instruction.  do_bp passes regs->csr_era straight to
+// force_sig_fault(SIGTRAP, TRAP_BRKPT, ...) and never adjusts era on the
+// signal path (arch/loongarch/kernel/traps.c).
+const breakpointPCAdjust = 0

debug/regs_linux_riscv64.go

@@ -126,5 +126,9 @@ func (r *Regs) RegValue(name string) (uint64, bool) {
 // breakpointInsn is the software breakpoint instruction (EBREAK).
 var breakpointInsn = []byte{0x73, 0x00, 0x10, 0x00} // ebreak
 
-// breakpointPCAdjust is how far PC is past the breakpoint instruction after a trap.
-const breakpointPCAdjust = 4
+// breakpointPCAdjust is how far PC is past the breakpoint instruction after
+// a trap: 0, because the kernel delivers the EBREAK SIGTRAP with sepc still
+// on the ebreak.  handle_break passes regs->epc straight to
+// force_sig_fault(SIGTRAP, TRAP_BRKPT, ...) and only the kernel-internal
+// WARN/CFI paths advance epc (arch/riscv/kernel/traps.c).
+const breakpointPCAdjust = 0

debug/repl.go

@@ -7,9 +7,10 @@ package debug
 
 import (
 	"bufio"
+	"cmp"
 	"fmt"
 	"io"
-	"sort"
+	"slices"
 	"strconv"
 	"strings"
 )
@@ -32,7 +33,7 @@ func REPL(s *Session, bm *Breakpoints, codeBase uint64, funcOffset, funcSize, ar
 	entryAddr := codeBase + uint64(funcOffset)
 
 	fmt.Printf("stopped at function entry: %#x (%d bytes)\n", entryAddr, funcSize)
-	fmt.Println("commands: break <label|addr> | step [n] | continue | disas [n] | regs | where | x <addr> [len] | w <addr> <val...> | labels | quit")
+	fmt.Println("commands: break <label|addr|line> | step [n] | continue | disas [n] | regs | where | x <addr> [len] | w <addr> <val...> | labels | quit")
 
 	scanner := bufio.NewScanner(in)
 
@@ -93,7 +94,7 @@ func REPL(s *Session, bm *Breakpoints, codeBase uint64, funcOffset, funcSize, ar
 			regs, _ := s.GetRegs()
 			pc := regs.GetPC()
 			text, instLen, _ := s.Disassemble(pc)
-			if strings.HasPrefix(strings.ToLower(text), "call") || strings.HasPrefix(strings.ToLower(text), "bl") {
+			if isCallInsn(text) {
 				afterAddr := pc + uint64(instLen)
 				_, err := bm.Set(afterAddr, "(next)")
 				if err != nil {
@@ -108,6 +109,21 @@ func REPL(s *Session, bm *Breakpoints, codeBase uint64, funcOffset, funcSize, ar
 					bm.Clear(afterAddr)
 					continue
 				}
+				if s.Exited() {
+					bm.Clear(afterAddr)
+					fmt.Println("debuggee exited")
+					continue
+				}
+				if sig := s.LastSignal(); sig != 0 {
+					bm.Clear(afterAddr)
+					regs, _ := s.GetRegs()
+					fmt.Printf("stopped on signal %v at %#x\n", sig, regs.GetPC())
+					continue
+				}
+				// Fetch the registers after the stop: the trap must be
+				// evaluated against the real PC, not the pre-Continue
+				// snapshot, and a stale SetRegs would clobber live state.
+				regs, _ = s.GetRegs()
 				bm.HandleTrap(&regs)
 				bm.Clear(afterAddr)
 			} else {
@@ -143,9 +159,21 @@ func REPL(s *Session, bm *Breakpoints, codeBase uint64, funcOffset, funcSize, ar
 				bm.Clear(retAddr)
 				continue
 			}
-			if !s.Exited() {
-				bm.HandleTrap(&regs)
+			if s.Exited() {
+				bm.Clear(retAddr)
+				fmt.Println("debuggee exited")
+				continue
 			}
+			if sig := s.LastSignal(); sig != 0 {
+				bm.Clear(retAddr)
+				regs, _ := s.GetRegs()
+				fmt.Printf("stopped on signal %v at %#x\n", sig, regs.GetPC())
+				continue
+			}
+			// Fetch the registers after the stop, as the continue case
+			// does: HandleTrap must see the PC the trap left behind.
+			regs, _ = s.GetRegs()
+			bm.HandleTrap(&regs)
 			bm.Clear(retAddr)
 			if s.Exited() {
 				fmt.Println("debuggee exited")
@@ -171,6 +199,15 @@ func REPL(s *Session, bm *Breakpoints, codeBase uint64, funcOffset, funcSize, ar
 					fmt.Println("debuggee exited")
 					break
 				}
+				if sig := s.LastSignal(); sig != 0 {
+					// A genuine signal-delivery-stop (a fault): report it
+					// and return to the prompt.  Continuing would restart
+					// the faulting instruction and fault forever.
+					regs, _ := s.GetRegs()
+					fmt.Printf("stopped on signal %v at %#x (func+%#x)\n",
+						sig, regs.GetPC(), regs.GetPC()-codeBase-uint64(funcOffset))
+					break
+				}
 				reason, wpAddr := s.StopInfo()
 				if reason == StopWatchpoint {
 					fmt.Printf("watchpoint hit at %#x\n", wpAddr)
@@ -196,7 +233,7 @@ func REPL(s *Session, bm *Breakpoints, codeBase uint64, funcOffset, funcSize, ar
 
 		case "break", "b":
 			if len(parts) < 2 {
-				fmt.Println("usage: break <label|addr|line> [if <reg> <op> <val>]")
+				fmt.Println("usage: break <label|addr|line> [if <reg> <op> <val|reg|*addr>]")
 				continue
 			}
 			var addr uint64
@@ -221,13 +258,27 @@ func REPL(s *Session, bm *Breakpoints, codeBase uint64, funcOffset, funcSize, ar
 				reg := strings.ToLower(parts[3])
 				op := parts[4]
 				operand := parts[5]
-				if val, err := strconv.ParseUint(operand, 0, 64); err == nil {
-					cond = &Condition{Reg: reg, Op: op, Value: val}
-				} else {
-					cond = &Condition{Reg: reg, Op: op, Reg2: strings.ToLower(operand)}
+				switch {
+				case strings.HasPrefix(operand, "*"):
+					// Memory operand: compare against the 8-byte word at
+					// the address, resolved in the debuggee when the
+					// breakpoint is evaluated.
+					addr, err := strconv.ParseUint(strings.TrimPrefix(operand, "*"), 0, 64)
+					if err != nil {
+						fmt.Printf("invalid memory operand: %s\n", operand)
+						continue
+					}
+					cond = &Condition{Reg: reg, Op: op, MemAddr: addr}
+				default:
+					val, err := strconv.ParseUint(operand, 0, 64)
+					if err == nil {
+						cond = &Condition{Reg: reg, Op: op, Value: val}
+					} else {
+						cond = &Condition{Reg: reg, Op: op, Reg2: strings.ToLower(operand)}
+					}
 				}
 			} else if len(parts) >= 4 && parts[2] == "if" {
-				fmt.Println("usage: break <label|addr> if <reg> <op> <value|reg>")
+				fmt.Println("usage: break <label|addr|line> if <reg> <op> <value|reg|*addr>")
 				continue
 			}
 			bp, err := bm.SetWithCond(addr, label, cond)
@@ -237,7 +288,7 @@ func REPL(s *Session, bm *Breakpoints, codeBase uint64, funcOffset, funcSize, ar
 			}
 			condStr := ""
 			if cond != nil {
-				condStr = fmt.Sprintf(" if %s %s %#x", cond.Reg, cond.Op, cond.Value)
+				condStr = " if " + cond.String()
 			}
 			fmt.Printf("breakpoint set: %s at %#x (func+%#x)%s\n", bp.Label, bp.Addr, bp.Addr-codeBase-uint64(funcOffset), condStr)
 
@@ -277,7 +328,11 @@ func REPL(s *Session, bm *Breakpoints, codeBase uint64, funcOffset, funcSize, ar
 				addr, _ = resolveAddr(parts[1], codeBase, uint64(funcOffset), labels)
 			}
 			if len(parts) > 2 {
-				length, _ = strconv.Atoi(parts[2])
+				// A malformed or non-positive length would panic
+				// ReadMemory's make; fall back to the default instead.
+				if n, err := strconv.Atoi(parts[2]); err == nil && n > 0 {
+					length = n
+				}
 			}
 			mem, err := s.ReadMemory(addr, length)
 			if err != nil {
@@ -336,10 +391,8 @@ func REPL(s *Session, bm *Breakpoints, codeBase uint64, funcOffset, funcSize, ar
 			}
 
 		case "labels", "l":
-			sorted := make([]Label, len(labels))
-			copy(sorted, labels)
-			sort.Slice(sorted, func(i, j int) bool { return sorted[i].Offset < sorted[j].Offset })
-			for _, l := range sorted {
+			slices.SortFunc(labels, func(a, b Label) int { return cmp.Compare(a.Offset, b.Offset) })
+			for _, l := range labels {
 				fmt.Printf("  func+%#04x  %s\n", l.Offset, l.Name)
 			}
 
@@ -369,7 +422,10 @@ func REPL(s *Session, bm *Breakpoints, codeBase uint64, funcOffset, funcSize, ar
 			fmt.Println()
 
 		case "help", "h", "?":
-			fmt.Printf(`  break <label|addr> [if <reg> <op> <val>]  set a breakpoint
+			fmt.Printf(`  break <label|addr|line> [if <reg> <op> <val|reg|*addr>]
+                       set a breakpoint, optionally conditional on a
+                       register compared to a constant, a register, or the
+                       8-byte word at *addr
   delete <label|addr>  remove a breakpoint
   info break           list all breakpoints
   watch <addr> [r|w] [size]  set a hardware watchpoint (write by default)
@@ -463,8 +519,8 @@ func REPL(s *Session, bm *Breakpoints, codeBase uint64, funcOffset, funcSize, ar
 		case "unwatch":
 			if len(parts) >= 2 {
 				slot, err := strconv.Atoi(parts[1])
-				if err != nil || slot < 0 || slot > 3 {
-					fmt.Println("usage: unwatch [<slot>]")
+				if err != nil || slot < 0 || slot >= maxWatchpoints() {
+					fmt.Printf("usage: unwatch [<slot 0-%d>]\n", maxWatchpoints()-1)
 					continue
 				}
 				if err := s.ClearWatchpoint(slot); err != nil {

debug/stopinfo_linux.go

@@ -6,6 +6,7 @@
 package debug
 
 import (
+	"encoding/binary"
 	"syscall"
 	"unsafe"
 )
@@ -61,8 +62,15 @@ func (s *Session) StopInfo() (StopReason, uint64) {
 	case trapBRKPT:
 		return StopBreakpoint, 0
 	case trapHWBRKPT:
-		addr := *(*uint64)(unsafe.Add(unsafe.Pointer(&info), 16))
-		return StopWatchpoint, addr
+		// si_addr sits at struct offset 16 (12 bytes of signo/errno/code
+		// plus 4 bytes of union alignment).  The siginfo buffer is only
+		// 4-byte aligned, so the address is read byte-wise to keep the
+		// load aligned on riscv64 and loong64.  What si_addr names is
+		// architecture-specific (the data address on arm64, the
+		// instruction pointer on x86), so the per-architecture
+		// archWatchpointAddr resolves it to the watched address.
+		addr := binary.LittleEndian.Uint64(info._pad[4:12])
+		return StopWatchpoint, archWatchpointAddr(s, addr)
 	default:
 		return StopSingleStep, 0
 	}

debug/target_linux_arm64.go

@@ -28,15 +28,7 @@ func RunTarget(asmPath, funcName, argsFile, tmpDir string) error {
 		return fmt.Errorf("debug target: parse: %v", errs[0])
 	}
 
-	var img *asm.Image
-	switch "arm64" {
-	case "arm64":
-		img, err = asm.AssembleFileARM64(file)
-	case "riscv64":
-		img, err = asm.AssembleFileRISCV(file)
-	case "loong64":
-		img, err = asm.AssembleFileLOONG64(file)
-	}
+	img, err := asm.AssembleFileARM64(file)
 	if err != nil {
 		return fmt.Errorf("debug target: assemble: %w", err)
 	}

debug/target_linux_loong64.go

@@ -28,15 +28,7 @@ func RunTarget(asmPath, funcName, argsFile, tmpDir string) error {
 		return fmt.Errorf("debug target: parse: %v", errs[0])
 	}
 
-	var img *asm.Image
-	switch "loong64" {
-	case "arm64":
-		img, err = asm.AssembleFileARM64(file)
-	case "riscv64":
-		img, err = asm.AssembleFileRISCV(file)
-	case "loong64":
-		img, err = asm.AssembleFileLOONG64(file)
-	}
+	img, err := asm.AssembleFileLOONG64(file)
 	if err != nil {
 		return fmt.Errorf("debug target: assemble: %w", err)
 	}

debug/tracer.go

@@ -12,10 +12,11 @@ type tracer interface {
 	Peek(addr uint64) (uint64, error)
 	Poke(addr uint64, val uint64) error
 	SetRegs(regs *Regs) error
+	Step() error
 	Pid() int
 }
 
-// mockTracer records Peek/Poke calls and provides fake register state.
+// mockTracer records Peek/Poke/Step calls and provides fake register state.
 type mockTracer struct {
 	mem   map[uint64]byte
 	peeks []uint64
@@ -23,7 +24,8 @@ type mockTracer struct {
 		addr uint64
 		val  uint64
 	}
-	regs *Regs
+	steps int
+	regs  *Regs
 }
 
 func newMockTracer() *mockTracer {
@@ -57,4 +59,8 @@ func (m *mockTracer) SetRegs(regs *Regs) error {
 	m.regs = regs
 	return nil
 }
+func (m *mockTracer) Step() error {
+	m.steps++
+	return nil
+}
 func (m *mockTracer) Pid() int { return 42 }

debug/watchpoint_linux_amd64.go

@@ -8,10 +8,48 @@ package debug
 import (
 	"fmt"
 	"syscall"
+	"unsafe"
 )
 
 // Hardware watchpoint support via x86-64 debug registers (DR0-DR3, DR7).
 
+// The kernel translates PTRACE_POKEUSER/PEEKUSER offsets inside
+// [offsetof(struct user, u_debugreg[0]), u_debugreg[7]] to DR0-DR7
+// (arch/x86/kernel/ptrace.c, arch_ptrace).  sys/user.h places u_debugreg at
+// 0x350: DR0-DR3 are 0x350/0x358/0x360/0x368, DR6 (status) is 0x380 and
+// DR7 (control) is 0x388.  Offsets below 0x350 write user_regs_struct
+// fields (r15 at 0x0, r10 at 0x38), not debug registers.
+const (
+	drOffset = 0x350 // offsetof(struct user, u_debugreg[0]), DR0
+	dr6Off   = 0x380 // offsetof(struct user, u_debugreg[6]), DR6
+	dr7Off   = 0x388 // offsetof(struct user, u_debugreg[7]), DR7
+)
+
+// archWatchpointAddr resolves the address of the watchpoint that fired.
+// x86 delivers si_addr = the instruction pointer of the trapping access
+// (arch/x86/kernel/ptrace.c send_sigtrap passes regs->ip), so the watched
+// data address is recovered from DR6's slot bits (B0-B3, positive polarity
+// through PEEKUSER) and the matching DR0-DR3.
+func archWatchpointAddr(s *Session, siAddr uint64) uint64 {
+	dr6, err := ptracePeekUser(s.pid, dr6Off)
+	if err != nil {
+		return siAddr
+	}
+	for slot := range 4 {
+		if dr6&(1<<slot) != 0 {
+			addr, err := ptracePeekUser(s.pid, drOffset+uintptr(slot*8))
+			if err == nil && addr != 0 {
+				return addr
+			}
+		}
+	}
+	return siAddr
+}
+
+// maxWatchpoints reports the number of hardware watchpoint slots the
+// architecture provides: four address registers, DR0-DR3.
+func maxWatchpoints() int { return 4 }
+
 // WatchpointType selects what triggers the watchpoint.
 type WatchpointType int
 
@@ -62,23 +100,11 @@ func (s *Session) SetWatchpoint(slot int, addr uint64, typ WatchpointType, size
 		return fmt.Errorf("debug: watchpoint size must be 1, 2, 4, or 8")
 	}
 
-	var drAddr uintptr
-	switch slot {
-	case 0:
-		drAddr = 0x0
-	case 1:
-		drAddr = 0x8
-	case 2:
-		drAddr = 0x10
-	case 3:
-		drAddr = 0x18
-	}
-
-	if err := ptracePokeUser(s.pid, drAddr, addr); err != nil {
+	if err := ptracePokeUser(s.pid, drOffset+uintptr(slot*8), addr); err != nil {
 		return fmt.Errorf("debug: set DR%d: %w", slot, err)
 	}
 
-	dr7, err := ptracePeekUser(s.pid, 0x38)
+	dr7, err := ptracePeekUser(s.pid, dr7Off)
 	if err != nil {
 		return fmt.Errorf("debug: read DR7: %w", err)
 	}
@@ -90,7 +116,7 @@ func (s *Session) SetWatchpoint(slot int, addr uint64, typ WatchpointType, size
 	mask := ^((uint64(1) << (2 * slot)) | (uint64(3) << (16 + 4*slot)) | (uint64(3) << (18 + 4*slot)))
 	dr7 = (dr7 & mask) | enableBit | rwBits | lenField
 
-	if err := ptracePokeUser(s.pid, 0x38, dr7); err != nil {
+	if err := ptracePokeUser(s.pid, dr7Off, dr7); err != nil {
 		return fmt.Errorf("debug: set DR7: %w", err)
 	}
 	s.wpSlots[slot] = true
@@ -105,12 +131,12 @@ func (s *Session) ClearWatchpoint(slot int) error {
 	if !s.wpSlots[slot] {
 		return fmt.Errorf("debug: watchpoint slot %d is not in use", slot)
 	}
-	dr7, err := ptracePeekUser(s.pid, 0x38)
+	dr7, err := ptracePeekUser(s.pid, dr7Off)
 	if err != nil {
 		return err
 	}
 	dr7 &^= uint64(1) << (2 * slot)
-	if err := ptracePokeUser(s.pid, 0x38, dr7); err != nil {
+	if err := ptracePokeUser(s.pid, dr7Off, dr7); err != nil {
 		return err
 	}
 	s.wpSlots[slot] = false
@@ -119,7 +145,7 @@ func (s *Session) ClearWatchpoint(slot int) error {
 
 // ClearAllWatchpoints removes all hardware watchpoints.
 func (s *Session) ClearAllWatchpoints() error {
-	for slot := range 4 {
+	for slot := range maxWatchpoints() {
 		if s.wpSlots[slot] {
 			if err := s.ClearWatchpoint(slot); err != nil {
 				return err
@@ -146,16 +172,21 @@ func ptracePokeUser(pid int, offset uintptr, val uint64) error {
 }
 
 func ptracePeekUser(pid int, offset uintptr) (uint64, error) {
+	// x86 PEEKUSR writes the word to the user-space pointer in data
+	// (arch/x86/kernel/ptrace.c uses put_user); passing 0 there fails with
+	// EFAULT, so the word is read through a real address.
 	const ptracePeekuser = 3
-	val, _, errno := syscall.Syscall6(
+	var word uint64
+	_, _, errno := syscall.Syscall6(
 		syscall.SYS_PTRACE,
 		uintptr(ptracePeekuser),
 		uintptr(pid),
 		offset,
-		0, 0, 0,
+		uintptr(unsafe.Pointer(&word)),
+		0, 0,
 	)
 	if errno != 0 {
 		return 0, errno
 	}
-	return uint64(val), nil
+	return word, nil
 }

debug/watchpoint_linux_arm64.go

@@ -12,7 +12,7 @@ import (
 )
 
 // Hardware watchpoint support via arm64 debug registers (DBGWVR/DBGWCR).
-// Accessed via PTRACE_SETREGSET with NT_ARM_HW_BREAK.
+// Accessed via PTRACE_GETREGSET/SETREGSET with NT_ARM_HW_WATCH.
 
 // WatchpointType selects what triggers the watchpoint.
 type WatchpointType int
@@ -22,26 +22,35 @@ const (
 	WatchRead  WatchpointType = 3
 )
 
-const maxWatchpoints = 16
+// maxWatchpoints reports the number of hardware watchpoint slots the
+// architecture provides: DBGWVR0-DBGWCR15.
+func maxWatchpoints() int { return 16 }
 
-// hwBreakState mirrors the kernel's struct user_hwdebug_state.
-type hwBreakState struct {
+// hwWatchState mirrors the kernel's struct user_hwdebug_state.
+type hwWatchState struct {
 	DbgInfo uint32
 	_pad    [4]byte
-	DbgRegs [16]hwBreakReg
+	DbgRegs [16]hwWatchReg
 }
 
-type hwBreakReg struct {
+type hwWatchReg struct {
 	Addr uint64
 	Ctrl uint64
 }
 
-const (
-	ntArmHWBreak = 0x403 // NT_ARM_HW_BREAK
-)
+// ntArmHWWatch is NT_ARM_HW_WATCH (0x403), the watchpoint regset
+// (include/uapi/linux/elf.h; 0x402 is NT_ARM_HW_BREAK).  Watchpoints and
+// breakpoints live in different regsets with the same struct shape, so the
+// constant is named for what it arms to keep a future edit from arming
+// breakpoints instead.
+const ntArmHWWatch = 0x403
+
+// archWatchpointAddr resolves the address of the watchpoint that fired:
+// the arm64 kernel already reports the watched data address as si_addr.
+func archWatchpointAddr(s *Session, siAddr uint64) uint64 { return siAddr }
 
 func (s *Session) FindFreeWatchpointSlot() int {
-	for i := range maxWatchpoints {
+	for i := range maxWatchpoints() {
 		if !s.wpSlots[i] {
 			return i
 		}
@@ -50,7 +59,7 @@ func (s *Session) FindFreeWatchpointSlot() int {
 }
 
 func (s *Session) IsWatchpointSlotUsed(slot int) bool {
-	if slot < 0 || slot >= maxWatchpoints {
+	if slot < 0 || slot >= maxWatchpoints() {
 		return false
 	}
 	return s.wpSlots[slot]
@@ -58,27 +67,31 @@ func (s *Session) IsWatchpointSlotUsed(slot int) bool {
 
 // SetWatchpoint installs a hardware watchpoint on the given address.
 func (s *Session) SetWatchpoint(slot int, addr uint64, typ WatchpointType, size int) error {
-	if slot < 0 || slot >= maxWatchpoints {
-		return fmt.Errorf("debug: watchpoint slot must be 0-%d", maxWatchpoints-1)
+	if slot < 0 || slot >= maxWatchpoints() {
+		return fmt.Errorf("debug: watchpoint slot must be 0-%d", maxWatchpoints()-1)
 	}
 	if s.wpSlots[slot] {
 		return fmt.Errorf("debug: watchpoint slot %d already in use", slot)
 	}
 
-	state, err := s.getHWBreakState()
+	state, err := s.getHWWatchState()
 	if err != nil {
 		return fmt.Errorf("debug: read watchpoint state: %w", err)
 	}
 
-	if uint32(slot) >= state.DbgInfo {
-		return fmt.Errorf("debug: slot %d exceeds available watchpoints (%d)", slot, state.DbgInfo)
+	// MDSCR_EL1 packs (debug_arch << 8) | num_slots into dbg_info, so only
+	// the low byte counts slots.
+	if uint32(slot) >= state.DbgInfo&0xff {
+		return fmt.Errorf("debug: slot %d exceeds available watchpoints (%d)", slot, state.DbgInfo&0xff)
 	}
 
 	state.DbgRegs[slot].Addr = addr
+	// DBGWCR bits 3-4 select the access type: 01 load, 10 store, 11 either
+	// (ARM DDI 0487, DBGWCR<n>_EL1 watchpoint type field).
 	ctrl := uint64(1) // enable
 	switch typ {
 	case WatchWrite:
-		ctrl |= 1 << 3 // store only
+		ctrl |= 2 << 3 // store only
 	case WatchRead:
 		ctrl |= 3 << 3 // load+store
 	}
@@ -98,7 +111,7 @@ func (s *Session) SetWatchpoint(slot int, addr uint64, typ WatchpointType, size
 	ctrl |= bas << 5
 	state.DbgRegs[slot].Ctrl = ctrl
 
-	if err := s.setHWBreakState(state); err != nil {
+	if err := s.setHWWatchState(state); err != nil {
 		return fmt.Errorf("debug: set watchpoint: %w", err)
 	}
 
@@ -107,20 +120,20 @@ func (s *Session) SetWatchpoint(slot int, addr uint64, typ WatchpointType, size
 }
 
 func (s *Session) ClearWatchpoint(slot int) error {
-	if slot < 0 || slot >= maxWatchpoints {
-		return fmt.Errorf("debug: watchpoint slot must be 0-%d", maxWatchpoints-1)
+	if slot < 0 || slot >= maxWatchpoints() {
+		return fmt.Errorf("debug: watchpoint slot must be 0-%d", maxWatchpoints()-1)
 	}
 	if !s.wpSlots[slot] {
 		return fmt.Errorf("debug: watchpoint slot %d is not in use", slot)
 	}
 
-	state, err := s.getHWBreakState()
+	state, err := s.getHWWatchState()
 	if err != nil {
 		return err
 	}
 	state.DbgRegs[slot].Addr = 0
 	state.DbgRegs[slot].Ctrl = 0
-	if err := s.setHWBreakState(state); err != nil {
+	if err := s.setHWWatchState(state); err != nil {
 		return err
 	}
 	s.wpSlots[slot] = false
@@ -128,7 +141,7 @@ func (s *Session) ClearWatchpoint(slot int) error {
 }
 
 func (s *Session) ClearAllWatchpoints() error {
-	for slot := 0; slot < maxWatchpoints; slot++ {
+	for slot := range maxWatchpoints() {
 		if s.wpSlots[slot] {
 			if err := s.ClearWatchpoint(slot); err != nil {
 				return err
@@ -138,8 +151,8 @@ func (s *Session) ClearAllWatchpoints() error {
 	return nil
 }
 
-func (s *Session) getHWBreakState() (*hwBreakState, error) {
-	var state hwBreakState
+func (s *Session) getHWWatchState() (*hwWatchState, error) {
+	var state hwWatchState
 	iovec := syscall.Iovec{
 		Base: (*byte)(unsafe.Pointer(&state)),
 		Len:  uint64(unsafe.Sizeof(state)),
@@ -148,7 +161,7 @@ func (s *Session) getHWBreakState() (*hwBreakState, error) {
 		syscall.SYS_PTRACE,
 		uintptr(syscall.PTRACE_GETREGSET),
 		uintptr(s.pid),
-		uintptr(ntArmHWBreak),
+		uintptr(ntArmHWWatch),
 		uintptr(unsafe.Pointer(&iovec)),
 		0, 0,
 	)
@@ -158,7 +171,7 @@ func (s *Session) getHWBreakState() (*hwBreakState, error) {
 	return &state, nil
 }
 
-func (s *Session) setHWBreakState(state *hwBreakState) error {
+func (s *Session) setHWWatchState(state *hwWatchState) error {
 	iovec := syscall.Iovec{
 		Base: (*byte)(unsafe.Pointer(state)),
 		Len:  uint64(unsafe.Sizeof(*state)),
@@ -167,7 +180,7 @@ func (s *Session) setHWBreakState(state *hwBreakState) error {
 		syscall.SYS_PTRACE,
 		uintptr(syscall.PTRACE_SETREGSET),
 		uintptr(s.pid),
-		uintptr(ntArmHWBreak),
+		uintptr(ntArmHWWatch),
 		uintptr(unsafe.Pointer(&iovec)),
 		0, 0,
 	)

debug/watchpoint_linux_loong64.go

@@ -8,10 +8,47 @@ package debug
 import (
 	"fmt"
 	"syscall"
+	"unsafe"
 )
 
-// Hardware watchpoint support for LoongArch via debug registers.
-// Uses PTRACE_POKEUSER/PEEKUSER to access HW watchpoint registers.
+// Hardware watchpoint support via the NT_LOONGARCH_HW_WATCH regset.
+//
+// The kernel's PTRACE_POKEUSER on loong64 accepts only the user_pt_regs
+// indices 0-34 (GPRs, orig_a0, era, badv, per
+// arch/loongarch/include/uapi/asm/ptrace.h), so there is no debug-register
+// window to poke.  The real interface is PTRACE_GETREGSET/SETREGSET on
+// NT_LOONGARCH_HW_WATCH (0xa06, include/uapi/linux/elf.h) with struct
+// user_watch_state_v2 (arch/loongarch/include/uapi/asm/ptrace.h): a dbg_info
+// word followed by 14 slots of {addr u64, mask u64, ctrl u32, pad u32}.
+// hw_break_get puts the slot count in the low byte of dbg_info
+// (arch/loongarch/kernel/ptrace.c, ptrace_hbp_get_resource_info) and
+// hw_break_set ignores dbg_info, reading addr, mask and ctrl per slot.
+
+const ntLoongHWWatch = 0xa06
+
+// loongWatchState mirrors the kernel's struct user_watch_state_v2.
+type loongWatchState struct {
+	DbgInfo uint64
+	DbgRegs [14]loongWatchReg
+}
+
+type loongWatchReg struct {
+	Addr uint64
+	Mask uint64
+	Ctrl uint32
+	Pad  uint32
+}
+
+// Control word bit layout (arch/loongarch/include/asm/hw_breakpoint.h):
+// bits 1-4 privilege enables (CTRL_PLV3_ENABLE, 0x10, covers user mode),
+// bits 8-9 access type (LOAD 1<<0, STORE 1<<1), bits 10-11 length
+// (0=8 bytes, 1=4, 2=2, 3=1, inverted like the hardware FWP cfg).
+const (
+	loongCtrlPLV3Enable = 0x10
+	loongTypeLoad       = 1 << 8
+	loongTypeStore      = 2 << 8
+	loongLenShift       = 10
+)
 
 // WatchpointType selects what triggers the watchpoint.
 type WatchpointType int
@@ -21,10 +58,16 @@ const (
 	WatchRead  WatchpointType = 3
 )
 
-const maxWatchpoints = 4
+// maxWatchpoints reports the slot capacity of the regset struct; the number
+// the hardware actually provides is read from dbg_info at arm time.
+func maxWatchpoints() int { return len(loongWatchState{}.DbgRegs) }
+
+// archWatchpointAddr resolves the address of the watchpoint that fired:
+// the loongarch kernel already reports the accessed address as si_addr.
+func archWatchpointAddr(s *Session, siAddr uint64) uint64 { return siAddr }
 
 func (s *Session) FindFreeWatchpointSlot() int {
-	for i := range maxWatchpoints {
+	for i := range maxWatchpoints() {
 		if !s.wpSlots[i] {
 			return i
 		}
@@ -33,53 +76,56 @@ func (s *Session) FindFreeWatchpointSlot() int {
 }
 
 func (s *Session) IsWatchpointSlotUsed(slot int) bool {
-	if slot < 0 || slot >= maxWatchpoints {
+	if slot < 0 || slot >= maxWatchpoints() {
 		return false
 	}
 	return s.wpSlots[slot]
 }
 
-// SetWatchpoint installs a hardware watchpoint.
+// SetWatchpoint installs a hardware watchpoint on the given address.
 func (s *Session) SetWatchpoint(slot int, addr uint64, typ WatchpointType, size int) error {
-	if slot < 0 || slot >= maxWatchpoints {
-		return fmt.Errorf("debug: watchpoint slot must be 0-%d", maxWatchpoints-1)
+	if slot < 0 || slot >= maxWatchpoints() {
+		return fmt.Errorf("debug: watchpoint slot must be 0-%d", maxWatchpoints()-1)
 	}
 	if s.wpSlots[slot] {
 		return fmt.Errorf("debug: watchpoint slot %d already in use", slot)
 	}
-	if size != 1 && size != 2 && size != 4 && size != 8 {
+
+	var ctrlType uint32
+	switch typ {
+	case WatchWrite:
+		ctrlType = loongTypeStore
+	case WatchRead:
+		ctrlType = loongTypeLoad | loongTypeStore
+	}
+	var lenBits uint32
+	switch size {
+	case 1:
+		lenBits = 3
+	case 2:
+		lenBits = 2
+	case 4:
+		lenBits = 1
+	case 8:
+		lenBits = 0
+	default:
 		return fmt.Errorf("debug: watchpoint size must be 1, 2, 4, or 8")
 	}
 
-	// LoongArch debug registers: DBGWVR (watchpoint value) and DBGWCR (watchpoint control).
-	// Accessed via PTRACE_POKEUSER at architecture-specific offsets.
-	if err := ptracePokeUser(s.pid, uintptr(0x1000+slot*8), addr); err != nil {
-		return fmt.Errorf("debug: set watchpoint address: %w", err)
+	state, err := s.getLoongWatchState()
+	if err != nil {
+		return fmt.Errorf("debug: read watchpoint state: %w", err)
+	}
+	if uint64(slot) >= state.DbgInfo&0xff {
+		return fmt.Errorf("debug: slot %d exceeds available watchpoints (%d)", slot, state.DbgInfo&0xff)
 	}
 
-	// DBGWCR: enable + type + size.
-	var wcr uint64 = 1 // enable
-	switch typ {
-	case WatchWrite:
-		wcr |= 1 << 3 // store
-	case WatchRead:
-		wcr |= 3 << 3 // load+store
-	}
-	var sizeBits uint64
-	switch size {
-	case 1:
-		sizeBits = 0
-	case 2:
-		sizeBits = 1
-	case 4:
-		sizeBits = 2
-	case 8:
-		sizeBits = 3
-	}
-	wcr |= sizeBits << 5
+	state.DbgRegs[slot].Addr = addr
+	state.DbgRegs[slot].Mask = 0
+	state.DbgRegs[slot].Ctrl = loongCtrlPLV3Enable | ctrlType | lenBits<<loongLenShift
 
-	if err := ptracePokeUser(s.pid, uintptr(0x1001+slot*8), wcr); err != nil {
-		return fmt.Errorf("debug: set watchpoint control: %w", err)
+	if err := s.setLoongWatchState(state); err != nil {
+		return fmt.Errorf("debug: set watchpoint: %w", err)
 	}
 
 	s.wpSlots[slot] = true
@@ -87,14 +133,21 @@ func (s *Session) SetWatchpoint(slot int, addr uint64, typ WatchpointType, size
 }
 
 func (s *Session) ClearWatchpoint(slot int) error {
-	if slot < 0 || slot >= maxWatchpoints {
-		return fmt.Errorf("debug: watchpoint slot must be 0-%d", maxWatchpoints-1)
+	if slot < 0 || slot >= maxWatchpoints() {
+		return fmt.Errorf("debug: watchpoint slot must be 0-%d", maxWatchpoints()-1)
 	}
 	if !s.wpSlots[slot] {
 		return fmt.Errorf("debug: watchpoint slot %d is not in use", slot)
 	}
 
-	if err := ptracePokeUser(s.pid, uintptr(0x1001+slot*8), 0); err != nil {
+	state, err := s.getLoongWatchState()
+	if err != nil {
+		return err
+	}
+	state.DbgRegs[slot].Addr = 0
+	state.DbgRegs[slot].Mask = 0
+	state.DbgRegs[slot].Ctrl = 0
+	if err := s.setLoongWatchState(state); err != nil {
 		return err
 	}
 	s.wpSlots[slot] = false
@@ -102,7 +155,7 @@ func (s *Session) ClearWatchpoint(slot int) error {
 }
 
 func (s *Session) ClearAllWatchpoints() error {
-	for slot := 0; slot < maxWatchpoints; slot++ {
+	for slot := range maxWatchpoints() {
 		if s.wpSlots[slot] {
 			if err := s.ClearWatchpoint(slot); err != nil {
 				return err
@@ -112,14 +165,37 @@ func (s *Session) ClearAllWatchpoints() error {
 	return nil
 }
 
-func ptracePokeUser(pid int, offset uintptr, val uint64) error {
-	const ptracePokeuser = 6
+func (s *Session) getLoongWatchState() (*loongWatchState, error) {
+	var state loongWatchState
+	iovec := syscall.Iovec{
+		Base: (*byte)(unsafe.Pointer(&state)),
+		Len:  uint64(unsafe.Sizeof(state)),
+	}
 	_, _, errno := syscall.Syscall6(
 		syscall.SYS_PTRACE,
-		uintptr(ptracePokeuser),
-		uintptr(pid),
-		offset,
-		uintptr(val),
+		uintptr(syscall.PTRACE_GETREGSET),
+		uintptr(s.pid),
+		uintptr(ntLoongHWWatch),
+		uintptr(unsafe.Pointer(&iovec)),
+		0, 0,
+	)
+	if errno != 0 {
+		return nil, errno
+	}
+	return &state, nil
+}
+
+func (s *Session) setLoongWatchState(state *loongWatchState) error {
+	iovec := syscall.Iovec{
+		Base: (*byte)(unsafe.Pointer(state)),
+		Len:  uint64(unsafe.Sizeof(*state)),
+	}
+	_, _, errno := syscall.Syscall6(
+		syscall.SYS_PTRACE,
+		uintptr(syscall.PTRACE_SETREGSET),
+		uintptr(s.pid),
+		uintptr(ntLoongHWWatch),
+		uintptr(unsafe.Pointer(&iovec)),
 		0, 0,
 	)
 	if errno != 0 {
@@ -127,18 +203,3 @@ func ptracePokeUser(pid int, offset uintptr, val uint64) error {
 	}
 	return nil
 }
-
-func ptracePeekUser(pid int, offset uintptr) (uint64, error) {
-	const ptracePeekuser = 3
-	val, _, errno := syscall.Syscall6(
-		syscall.SYS_PTRACE,
-		uintptr(ptracePeekuser),
-		uintptr(pid),
-		offset,
-		0, 0, 0,
-	)
-	if errno != 0 {
-		return 0, errno
-	}
-	return uint64(val), nil
-}

debug/watchpoint_linux_riscv64.go

@@ -7,11 +7,16 @@ package debug
 
 import (
 	"fmt"
-	"syscall"
 )
 
-// Hardware watchpoint support for RISC-V via Sdtrig trigger registers.
-// Uses PTRACE_POKEUSER/PEEKUSER to access debug registers.
+// Hardware watchpoints are not reachable through the riscv64 kernel ptrace
+// interface.  arch/riscv/kernel/ptrace.c forwards every POKEUSER/PEEKUSER to
+// the generic ptrace_request, and the riscv user_regset view contains only
+// the GPR, FP and vector regsets: there is no debug-register or trigger
+// regset, and offsets outside the view fail with EIO.  The Sdtrig CSRs
+// (tselect/tdata1/tdata2) are not exposed to ptrace either.  Until the
+// kernel grows a trigger regset, SetWatchpoint reports the fact instead of
+// poking a window that does not exist.
 
 // WatchpointType selects what triggers the watchpoint.
 type WatchpointType int
@@ -21,10 +26,18 @@ const (
 	WatchRead  WatchpointType = 3
 )
 
-const maxWatchpoints = 4
+// maxWatchpoints reports the number of hardware watchpoint slots the
+// architecture provides.  riscv64 exposes none via ptrace; the bound exists
+// so the slot bookkeeping stays consistent.
+func maxWatchpoints() int { return 4 }
+
+// archWatchpointAddr resolves the address of the watchpoint that fired.
+// Unreachable in practice (watchpoints cannot be armed), but si_addr names
+// the accessed address where the kernel does report one.
+func archWatchpointAddr(s *Session, siAddr uint64) uint64 { return siAddr }
 
 func (s *Session) FindFreeWatchpointSlot() int {
-	for i := range maxWatchpoints {
+	for i := range maxWatchpoints() {
 		if !s.wpSlots[i] {
 			return i
 		}
@@ -33,115 +46,26 @@ func (s *Session) FindFreeWatchpointSlot() int {
 }
 
 func (s *Session) IsWatchpointSlotUsed(slot int) bool {
-	if slot < 0 || slot >= maxWatchpoints {
+	if slot < 0 || slot >= maxWatchpoints() {
 		return false
 	}
 	return s.wpSlots[slot]
 }
 
-// SetWatchpoint installs a hardware watchpoint.
+// SetWatchpoint always fails: the riscv64 kernel ptrace interface has no
+// hardware-watchpoint access.
 func (s *Session) SetWatchpoint(slot int, addr uint64, typ WatchpointType, size int) error {
-	if slot < 0 || slot >= maxWatchpoints {
-		return fmt.Errorf("debug: watchpoint slot must be 0-%d", maxWatchpoints-1)
-	}
-	if s.wpSlots[slot] {
-		return fmt.Errorf("debug: watchpoint slot %d already in use", slot)
-	}
-	if size != 1 && size != 2 && size != 4 && size != 8 {
-		return fmt.Errorf("debug: watchpoint size must be 1, 2, 4, or 8")
-	}
-
-	// RISC-V trigger registers: tdata1 encodes type/control, tdata2 holds address.
-	// The exact encoding depends on the trigger implementation (Sdtrig).
-	// Use PTRACE_POKEUSER to write to the trigger CSRs via the kernel's
-	// debug register interface.
-	if err := ptracePokeUser(s.pid, uintptr(0x1000+slot*8), addr); err != nil {
-		return fmt.Errorf("debug: set watchpoint address: %w", err)
-	}
-
-	// tdata1: set match control.  Mode=2 (data match), select=0, action=1 (debug exception).
-	var tdata1 uint64 = 2 << 60 // type = match (2)
-	tdata1 |= 1 << 0            // action = enter debug mode
-	tdata1 |= 1 << 7            // store (write) trigger
-	if typ == WatchRead {
-		tdata1 |= 1 << 6 // load trigger
-	}
-	// Size encoding: 0=1byte, 1=2byte, 2=4byte, 3=8byte.
-	var sizeBits uint64
-	switch size {
-	case 1:
-		sizeBits = 0
-	case 2:
-		sizeBits = 1
-	case 4:
-		sizeBits = 2
-	case 8:
-		sizeBits = 3
-	}
-	tdata1 |= sizeBits << 16 // size field
-
-	if err := ptracePokeUser(s.pid, uintptr(0x1001+slot*8), tdata1); err != nil {
-		return fmt.Errorf("debug: set watchpoint control: %w", err)
-	}
-
-	s.wpSlots[slot] = true
-	return nil
+	return fmt.Errorf("debug: hardware watchpoints are not supported by the riscv64 kernel ptrace interface")
 }
 
+// ClearWatchpoint always fails: no watchpoint can ever be armed.
 func (s *Session) ClearWatchpoint(slot int) error {
-	if slot < 0 || slot >= maxWatchpoints {
-		return fmt.Errorf("debug: watchpoint slot must be 0-%d", maxWatchpoints-1)
+	if slot < 0 || slot >= maxWatchpoints() {
+		return fmt.Errorf("debug: watchpoint slot must be 0-%d", maxWatchpoints()-1)
 	}
-	if !s.wpSlots[slot] {
-		return fmt.Errorf("debug: watchpoint slot %d is not in use", slot)
-	}
-
-	// Disable by clearing tdata1.
-	if err := ptracePokeUser(s.pid, uintptr(0x1001+slot*8), 0); err != nil {
-		return err
-	}
-	s.wpSlots[slot] = false
-	return nil
+	return fmt.Errorf("debug: watchpoint slot %d is not in use", slot)
 }
 
 func (s *Session) ClearAllWatchpoints() error {
-	for slot := 0; slot < maxWatchpoints; slot++ {
-		if s.wpSlots[slot] {
-			if err := s.ClearWatchpoint(slot); err != nil {
-				return err
-			}
-		}
-	}
 	return nil
 }
-
-func ptracePokeUser(pid int, offset uintptr, val uint64) error {
-	const ptracePokeuser = 6
-	_, _, errno := syscall.Syscall6(
-		syscall.SYS_PTRACE,
-		uintptr(ptracePokeuser),
-		uintptr(pid),
-		offset,
-		uintptr(val),
-		0, 0,
-	)
-	if errno != 0 {
-		return errno
-	}
-	return nil
-}
-
-func ptracePeekUser(pid int, offset uintptr) (uint64, error) {
-	const ptracePeekuser = 3
-	val, _, errno := syscall.Syscall6(
-		syscall.SYS_PTRACE,
-		uintptr(ptracePeekuser),
-		uintptr(pid),
-		offset,
-		0, 0, 0,
-	)
-	if errno != 0 {
-		return 0, errno
-	}
-	return uint64(val), nil
-}

docs/ARCHITECTURE.md

@@ -13,11 +13,13 @@ Three design goals shape everything below.
    So the centre of the toolkit is a hand-written lexer and a parser that
    produce a typed AST with source positions on every node.
 2. **Architecture as data, not code.**  Per-architecture differences (amd64,
-   arm64, riscv64, loong64) live in register and instruction *tables* (`arch`),
-   never in `if arch == …` branches scattered through the logic.  The
-   instruction tables are generated from the Go toolchain's own assembler
-   source (`just gen`), so adding or refreshing an architecture is a data
-   operation, not a coding one.
+   arm64, riscv64, loong64) live in register and instruction *tables* (`arch`)
+   and per-architecture encoders, rather than in `if arch == …` branches
+   threaded through the analysis; the arch tests that remain are dispatch and
+   policy points, such as which encoder a file name selects and which
+   registers the liveness pass audits.  The instruction tables are generated
+   from the Go toolchain's own assembler source (`just gen`), so refreshing an
+   architecture is a data operation, not a coding one.
 3. **Open integration surface.**  Everything the toolkit can do is reachable
    through two vendor-neutral interfaces: a CLI and an LSP server.  No editor
    owns the toolkit; the toolkit is offered to editors on standard terms.
@@ -35,19 +37,28 @@ flowchart TD
     ARCH["arch tables<br/>amd64 / arm64 / riscv64 / loong64"] --> LINT
     ARCH --> LSP
     LINT --> LSP
+    PAR --> ASM["asm<br/>encoders, image, object emitters"]
+    ASM --> VER["verify<br/>JIT mapping, ABI checks, fuzzing"]
+    ASM --> DBG["debug<br/>ptrace session"]
+    VER --> DBG
+    DIS["disasm<br/>golang.org/x/arch"] --> DBG
     FMT --> CLI["gasm CLI"]
     LINT --> CLI
     PAR --> CLI
     LEX --> CLI
+    ASM --> CLI
+    VER --> CLI
+    DBG --> CLI
+    DIS --> CLI
     LSP --> EDITOR["any LSP editor"]
 ```
 
 The lexer is the shared foundation: the parser builds the AST from it, the
 formatter re-spaces its tokens directly, and the language server uses it for
-semantic highlighting.  The phases follow a dependency chain: Phase 1 (static
-analysis) builds only on the AST, Phase 2 (the standalone assembler) emits
-object code, and Phases 3 (dynamic analysis) and 4 (the debugger) both consume
-the execution substrate that the assembler provides.
+semantic highlighting.  The packages follow a dependency chain: static analysis
+builds only on the AST, the standalone assembler emits object code, and both
+the dynamic analysis and the debugger consume the execution substrate the
+assembler provides.
 
 ## Packages
 
@@ -62,6 +73,7 @@ the execution substrate that the assembler provides.
 | `format` | canonical formatter over the token stream |
 | `lsp` | the language server |
 | `asm` | standalone assembler: encoders, image layout, object emitters |
+| `disasm` | disassembly backend over golang.org/x/arch |
 | `verify` | JIT execution, ABI checks, differential fuzzing |
 | `debug` | interactive ptrace debugger |
 | `cmd/gasm` | the CLI |
@@ -69,9 +81,11 @@ the execution substrate that the assembler provides.
 
 The boundaries matter as much as the responsibilities: `ast` records syntax
 only, and whether a name is a register or a label is left to `arch`, so the
-parser stays architecture-agnostic.  `asm` and `verify` are the only packages
-that touch machine code and executable memory, and `cmd/gasm` owns no logic
-beyond flags and output.
+parser stays architecture-agnostic.  `asm` produces the machine code, `verify`
+and `debug` are the two packages that map it executable (read-execute in
+`verify`, read-write-execute in the debuggee), and `cmd/gasm` is the CLI, with
+the verify sweep orchestration and the audit, scaffold and unified-diff
+helpers beside its flags and output.
 
 ### `token` and `lexer`
 
@@ -111,14 +125,17 @@ Register files are generated programmatically (the regular `R8`-`R15`,
 `X0`-`X15`, `Y0`-`Y15`, `Z0`-`Z31`, `K0`-`K7` ranges) plus the irregularly
 named registers listed explicitly.  Instruction names are **generated from the
 Go toolchain's own assembler source** (`cmd/internal/obj/<arch>/anames.go`,
-plus the common opcodes and the per-architecture front-end aliases such as the
-arm64 `B`/`BL` branches and the `.P`/`.W` load-store addressing suffixes) by
-`just gen`, so the tables always match what the real assembler accepts.  Each
-mnemonic maps to a summary and an optional operand-count range; counts are
-recorded only where unambiguous (`-1` disables the operand-count lint for that
-instruction) so the linter stays silent rather than guess.  For architectures
-with highly variable operand forms (arm64, riscv64, loong64) only a few
-fixed-arity instructions (`RET`, `NOP`, `JMP`, `CALL`) carry counts at all.
+plus the common opcodes in `cmd/internal/obj/util.go`) by `just gen`, so the
+tables always match what the real assembler accepts.  The spellings the
+toolchain's tables do not carry are hand-maintained instead: the front-end
+alias lists in `arch/arm64.go`, `arch/amd64.go` and `arch/loong64.go` (the
+arm64 `B`/`BL` branches among them), and the arm64 `.P`/`.W` load-store suffix
+stripping in `arch/arch.go`.  Each mnemonic maps to a summary and an optional
+operand-count range; counts are recorded only where unambiguous (`-1`
+disables the operand-count lint for that instruction) so the linter stays
+silent rather than guess.  For architectures with highly variable operand
+forms (arm64, riscv64, loong64) `relaxCounts` clears those counts, leaving
+`RET` and `NOP` with a range (`RET` alone on riscv64).
 
 ### `lint`
 
@@ -230,20 +247,20 @@ them from the standard LSP legend, so no editor-specific grammar is needed.
 
 ### `asm`
 
-The standalone assembler (Phase 2).  Its core is an amd64 instruction encoder:
+The standalone assembler.  Its core is an amd64 instruction encoder:
 a REX/ModR-M/SIB/displacement/immediate engine plus the scalar instruction set,
 with the Plan 9 operand order (source first) mapped onto the x86 encoding.
 Every encoding is validated by decoding it again with `golang.org/x/arch`, the
 one module dependency, which also backs the `gasm dis` listings.
 
-A **RISC-V encoder** (Phase 5, RV64IMAFDC + RVC compression) encodes the full
+A **RISC-V encoder** (RV64IMAFDC + RVC compression) encodes the full
 integer, atomic, float/double, FMA and CSR instruction sets with the MOV
 pseudo-instruction and SB/global symbol references (AUIPC pairs with
 R_RISCV_PCREL_HI20/LO12 relocations).  The encoder compresses eligible
 instructions to 16-bit RVC forms and is validated byte-for-byte against
 `GOARCH=riscv64 go tool asm`.
 
-A **LoongArch encoder** (Phase 5, LoongArch64) encodes the integer and
+A **LoongArch encoder** (LoongArch64) encodes the integer and
 floating-point instruction sets with the dual-form arithmetic mnemonics (3R
 vs 2RI12), the 16/21-bit branch families, the MOV pseudo-instruction and its
 constant materialisation (the dcon classification driving lu12i.w/ori/lu32i.d/
@@ -254,7 +271,7 @@ relocations).  Like the RISC-V encoder it is validated byte-for-byte against
 `GOARCH=loong64 go tool asm`, and its GOOBJ output is proven end-to-end by
 substituting it into a cross-compiled `go build` and linking with `cmd/link`.
 
-An **AArch64 encoder** (Phase 5, arm64) encodes the integer instruction set
+An **AArch64 encoder** (arm64) encodes the integer instruction set
 with the data-processing (shifted register and immediate forms), load/store
 (scaled unsigned immediate and unscaled9-bit immediate), conditional and
 unconditional branches, the MOV pseudo-instruction and its constant
@@ -290,11 +307,11 @@ registers are translated onto the hardware stack pointer: `x+N(FP)` becomes
 pointer is set up, with the matching Go prologue/epilogue generated, so the
 output is byte-identical to the Go assembler for these cases.  SIMD is handled
 by a VEX (AVX/AVX2) encoder (the two- and three-byte VEX prefixes with XMM/YMM
-registers) across eight operand forms: the three-operand NDS form, the
-two-operand reg/rm form, the immediate-shift form (plus the variable-count
-shifts, which share the NDS shape with the count in an XMM register or
-memory), the immediate shuffle form (`VPSHUFD`, `VPERMQ`), the
-three-operand-plus-immediate form (`VSHUFPD`,
+registers) over nine operand forms plus a dedicated move encoder: the
+three-operand NDS form, the two-operand reg/rm form, the immediate-shift form
+(plus the variable-count shifts, which share the NDS shape with the count in
+an XMM register or memory), the immediate shuffle form (`VPSHUFD`, `VPERMQ`),
+the three-operand-plus-immediate form (`VSHUFPD`,
 `VPERM2I128`, `VINSERTI128`), the lane-extract form (`VEXTRACTI128`,
 `VEXTRACTF128`, where the YMM source occupies the reg field and the XMM or
 memory destination r/m), the direction-sensitive moves (`VMOVDQU`, `VMOVUPD`,
@@ -339,10 +356,10 @@ b bit and the L'L rounding-control field (broadcast keeps the vector length
 and scales disp8 by the element size), and combine with the .Z zeroing
 suffix.  Every encoding is validated two ways: by
 round-trip decoding through `golang.org/x/arch`, and byte-for-byte against
-the machine code the real Go assembler emits, a comparison that holds for
-whole functions: all 27 functions of both kernels assemble to exactly the Go
-toolchain's bytes, the lone exception being the displacements of the
-static-constant loads, which the Go linker fills at link time.
+the machine code the real Go assembler emits; the parity suites carry that
+comparison over whole kernel files on all four architectures, with the
+relocation fields masked because the Go linker fills those displacements at
+link time.
 
 File-level assembly (`AssembleFile`) goes beyond single functions: it
 materialises the file's static symbols (`GLOBL`/`DATA`) in a data section
@@ -389,7 +406,7 @@ compiled packages it references.
 
 ### `verify`
 
-The dynamic-analysis substrate (Phase 3).  It JIT-loads assembled images into
+The dynamic-analysis substrate.  It JIT-loads assembled images into
 executable memory and invokes them directly, enabling differential testing,
 runtime ABI checks and coverage profiling.
 
@@ -409,9 +426,9 @@ every architecture too: `enterJITChecked` plants sentinels in the registers
 the Go ABI fixes across calls (amd64 `BP`/`R14`, arm64 `R29`/`R28`, riscv64
 `X27`, loong64 `R22`; the latter two keep no hardware frame pointer) and the
 raw return trampoline `leaveJITCheckedRaw` verifies them, restoring the
-saved registers before Go code resumes.  riscv64 is validated end to
-end under qemu-user emulation; arm64 shares the same stack convention and
-fix; loong64 stays ground-truth-only until hardware validation.
+saved registers before Go code resumes.  All three non-amd64 trampolines
+are validated end to end under qemu-user emulation, the loong64 one
+through its raw-address leave handoff.
 `gasm verify` runs the JIT checks when the host
 matches the kernel's architecture and the toolchain comparisons
 elsewhere.
@@ -425,10 +442,13 @@ The `gasm verify` CLI subcommand exposes this: it loads a file, reports the
 available functions and (with `-smoke`) calls each NOSPLIT function with zeroed
 arguments to confirm the trampoline round-trips.  The `-smoke` and `-abi`
 sweeps run in parallel and each inside a child process, so a function that
-faults is reported without ending the sweep.  `gasm verify --fuzz` combines
-ABI checks (sentinel registers, canary, stack bounds) with differential fuzz
-testing, comparing the JIT-assembled kernel against the portable Go reference
-bit-for-bit while verifying the ABI contract on every iteration.  When a fuzz
+faults is reported without ending the sweep; `-abi` is where the ABI check
+lives, fuzzing each function with sentinel values in the registers the Go ABI
+fixes across calls and a canary below `SP`, and reporting a violation on any
+iteration.  `gasm verify --fuzz` is the differential campaign instead: it
+JIT-loads the kernel and the `go tool asm` build of the same kernel and
+compares the output argument areas bit-for-bit, one child process per function
+so a crash on a partial function is reported rather than fatal.  When a fuzz
 iteration crashes or mismatches, `FuzzResult.CrashInput` stores the exact input
 for reproducibility.  `gasm verify --call <func> --buf name:size:pattern`
 invokes a single function with user-supplied buffers (patterns: zero, ones,
@@ -448,21 +468,30 @@ masked), reporting any encoding drift.
 The interactive debugger (all four architectures).  It launches the target
 function in a child process that maps the JIT code, calls
 `PTRACE_TRACEME`, and stops; the parent attaches via ptrace and controls
-execution.  Breakpoints are patched as INT3 bytes through `/proc/pid/mem`
-(PTRACE_PEEKTEXT is unreliable with Go's multi-threaded runtime).
+execution.  Breakpoints are patched through `/proc/pid/mem`: the one-byte
+`INT3` on amd64, the four-byte break instruction on the other three (arm64
+`BRK #0`, riscv64 `ebreak`, loong64 `break 0`).
 The child pins its goroutine to the OS thread with `runtime.LockOSThread`
 so the traced thread is the one executing JIT code.  The REPL provides
-single-step, register inspection (GPR + YMM/XMM via `PTRACE_GETFPREGS`),
+single-step, register inspection (the GPRs on every architecture; on amd64 the
+XMM set through `PTRACE_GETFPREGS` and the YMM set through `PTRACE_GETREGSET`
+on `NT_X86_XSTATE`; on the other three the FP/SIMD regset through
+`PTRACE_GETREGSET` on `NT_PRFPREG`),
 label resolution, named buffer allocation with pattern filling
 (`--buf name:size:pattern`: zero, ones, seq, or hex), and breakpoint
 management.  Breakpoints accept conditions
 (`break <label> if <reg> <op> <val>`, including register-against-register
-comparisons), and hardware watchpoints work on all four architectures.
+comparisons), and hardware watchpoints work on amd64 (the DR0-DR3 debug
+registers), arm64 (`NT_ARM_HW_WATCH`) and loong64 (`NT_LOONGARCH_HW_WATCH`);
+riscv64 reports that its kernel ptrace interface exposes no trigger regset.
+The ptrace path is validated at run time on amd64, where the session tests are
+built; arm64, riscv64 and loong64 compile and are covered by the
+architecture-neutral units (label and line tables, the breakpoint manager).
 For non-interactive use, `--script` runs REPL commands from a file (or
 stdin) and exits, `--timeout` kills the debuggee when a run hangs (the
 watchdog is armed before the ptrace attach, so a sandboxed debuggee cannot
 block it), and `--cover` runs to completion with a breakpoint on every
-label and reports which blocks executed.
+instruction and reports which instructions executed and how often.
 
 ### Extending the toolkit
 
@@ -498,9 +527,10 @@ sequenceDiagram
 Errors are produced where the parse or the encoding fails and become values at
 the CLI boundary: the parser returns a diagnostic list and never aborts a file,
 `AssembleFile` returns an error, and `cmd/gasm` prints what it has to stderr
-and returns a non-zero exit code.  The formatter and the linter take the same
-AST by a different route: `gasm fmt` re-spaces the token stream and `gasm lint`
-walks the parsed file, so neither depends on an encoding.
+and returns a non-zero exit code.  The formatter and the linter take different
+inputs from the assembler: `gasm fmt` re-spaces the token stream
+(`format.Source` lexes the source text itself) and `gasm lint` walks the parsed
+AST, so neither depends on an encoding.
 
 ## State and lifetime
 
@@ -521,9 +551,8 @@ walks the parsed file, so neither depends on an encoding.
 ## Dependencies
 
 - **`golang.org/x/arch`** (v0.30.0) is the one module dependency: it is the
-  disassembler backend (`gasm dis` and the debugger's listings) and the source
-  of the register metadata the encoder consults (`asm/reg.go`, `asm/vex.go`).
-  The tests additionally decode through it to validate the encodings.
+  disassembler backend (`gasm dis` and the debugger's listings).  The tests
+  additionally decode through it to validate the encodings.
 - **The Go toolchain**, as an oracle and never as a library: `go tool asm`
   supplies the object preamble and the ground truth for `gasm verify
   --ground-truth`, `go list -json -export` locates the archives of the packages

docs/CLI.md

@@ -3,9 +3,11 @@
 The reference below is taken from the program's own `--help`. If the two disagree, the
 program is right and this file is a defect.
 
-The same reference is installed as man pages: `just install-man` puts gasm(1) and one
-page per command into ~/.local/share/man (`MANDIR` overrides), and a test compares each
-page against the binary so the two cannot drift apart.
+The same reference is installed as man pages: `just install-man` puts gasm(1) and a page
+for every command except `version` (which gasm(1) itself documents) into
+~/.local/share/man (`MANDIR` overrides). A test in `cmd/gasm` keeps the two from
+drifting: it compares each page's flag set and SYNOPSIS line with the binary's own `-h`
+output, and gasm(1)'s COMMANDS list with the top-level help. The prose is not compared.
 
 ## Synopsis
 
@@ -58,7 +60,8 @@ Usage: gasm parse <file>
 ```
 
 Parse FILE and report syntax errors on stderr. On success, print how many
-declarations and TEXT functions the file contains.
+declarations and TEXT functions the file contains. FILE may be `-` to read
+standard input.
 
 ```sh
 gasm parse hello_amd64.s
@@ -155,7 +158,9 @@ recognisable suffix (most of GOROOT's, for example `cpu_x86.s`) are
 assembled. `raw` concatenates the functions and the data section into one
 self-consistent image; `elf` emits a relocatable object that links with the
 system toolchain; `goobj` emits the Go toolchain's own object format, which
-`cmd/link` consumes directly.
+`cmd/link` consumes directly, and is the one format that needs the toolchain
+installed: the object preamble is captured from `go tool asm` and the format
+version from `go version`. `raw` and `elf` need no toolchain at all.
 
 ```sh
 gasm asm hello_amd64.s
@@ -208,7 +213,7 @@ Usage: gasm verify [-smoke] [-abi] [-fuzz] [-ground-truth] [-profile] [-call] <f
 | `--abi-n` | 100 | ABI check iterations with varied inputs |
 | `--profile` | off | list the basic-block structure per function |
 | `--smoke` | off | call each NOSPLIT function with zeroed arguments |
-| `--call` | empty | invoke a single function with `--buf` instead of the sweeps |
+| `--call` | empty | invoke a single NOSPLIT function with `--buf` instead of the sweeps |
 | `--buf` | empty | buffer spec for `--call`: `name:size:pattern[,name:size:pattern]` |
 | `--args` | empty | scalar args for `--call`: `name=value[,name=value]` (decimal or `0x` hex) |
 | `--repeat` | 1 | number of times to repeat a `--call` invocation |
@@ -219,8 +224,8 @@ The JIT checks run when the host matches the file's architecture; the
 toolchain comparison works everywhere. `--fuzz`, `--smoke` and `--abi` run each
 function in its own child process, so a partial function that faults on random
 input is reported as `CRASH` instead of ending the sweep; `--call` with `--buf`
-invokes such a function with valid data. loong64 stays on the ground-truth path
-until hardware validation.
+invokes such a function with valid data. The function named by `--call` must be
+NOSPLIT: a function with a stack frame is refused with a diagnostic and exits 1.
 
 ```sh
 gasm verify --ground-truth hello_amd64.s
@@ -260,20 +265,21 @@ Usage: gasm debug <file.s> --func <name>
 | `-buf` | empty | buffer spec: `name:size:pattern[,name:size:pattern]` (zero, ones, seq or hex) |
 | `-args` | empty | file containing the ABI0 argument block |
 | `-script` | empty | run REPL commands from a file, one per line, and exit; `-` reads stdin |
-| `-timeout` | 0 | kill the debuggee after this duration, for headless `-script` runs |
+| `-timeout` | 0 | kill the debuggee after this duration, for headless `-script` runs; a timeout exits 3 |
 | `-cover` | off | run to completion with a breakpoint on every instruction and report which executed |
 
-The debugger spawns the debuggee from the `gasm` binary on `$PATH`, so install
-it first with `just install`; `go run` does not work for the traced child.
-Requires Linux (ptrace) and all four architectures are supported.
+The debugger re-executes the binary it is running as (`os.Executable()`) for the
+traced child, so the child is the same `gasm`, whether it is installed on `$PATH`
+or run with `go run ./cmd/gasm`; nothing has to be installed first. Requires
+Linux (ptrace), and all four architectures are supported.
 
 REPL commands:
 
 | Command | Effect |
 |---|---|
-| `break <label\|addr> [if <reg> <op> <val>]` | set a breakpoint, optionally conditional |
-| `delete <label\|addr>` | remove a breakpoint |
-| `info break` | list the breakpoints |
+| `break <label\|addr\|line> [if <reg> <op> <val\|reg\|*addr>]`, `b` | set a breakpoint; the condition compares a register with a constant, another register or the 8-byte word at `*addr` |
+| `delete <label\|addr>`, `d` | remove a breakpoint |
+| `info break`, `info breakpoints`, `info b` | list the breakpoints |
 | `step [n]`, `s` | single-step n instructions |
 | `next`, `n` | step over a CALL |
 | `finish`, `fin` | run until the function returns |
@@ -347,13 +353,18 @@ Usage: gasm audit-instructions [--corpus [dir]] [amd64|arm64|riscv64|loong64]
 
 Compare the gasm encoder for the given architecture (default amd64) against the
 installed `go tool asm` and print the diff: superset encodings (gasm-only
-spellings, shippable via `gasm asm --format goobj`), known-but-unencodable
-names (the encoder backlog) and go-only names (feature gaps). The Go side is
-probed black-box with a battery of operand shapes per mnemonic, so the audit
-tracks whatever toolchain `go env GOROOT` provides. On non-amd64
-architectures the backlog is an over-approximation: a name counts as encodable
-only when a probe shape assembles cleanly, so a name whose real forms the
-battery misses lands in the backlog.
+spellings, shippable via `gasm asm --format goobj`) and known-but-unencodable
+names (the encoder backlog). The Go side is probed black-box one bare mnemonic
+at a time, classified by the toolchain's diagnostic for an instruction it does
+not know, so the audit tracks whatever toolchain `go env GOROOT` provides; the
+gasm side answers from the encoder table on amd64 and from trial assembly over a
+battery of operand shapes on the other architectures. On non-amd64
+architectures the backlog is therefore an over-approximation: a name counts as
+encodable only when a probe shape assembles cleanly, so a name whose real forms
+the battery misses lands in the backlog. Names the toolchain knows and gasm does
+not cannot be enumerated by probing at all, because Go's table is visible only
+through names already in the gasm table; the report closes with a note saying
+so rather than listing them.
 
 ```sh
 gasm audit-instructions amd64
@@ -361,8 +372,9 @@ gasm audit-instructions amd64
 
 ```text
 gasm table (amd64, families excluded): 1542 mnemonics
-gasm encodable: 580   go tool asm recognized: 1542
-shared: 580
+gasm encodable: 587   go tool asm recognised: 1542
+shared: 587
+...
 ```
 
 With `--corpus` the audit changes shape: it assembles every `.s` file under
@@ -382,10 +394,12 @@ gasm audit-instructions --corpus "$(go env GOROOT)/src/crypto"
 
 ```text
 corpus /usr/local/go/src: 627 files (365 generic, attempted for all architectures)
-  assemble for every target architecture: 108 (17.2%)
-  amd64: 77/464 attempted
-    148  instruction not encodable
+  assemble for every target architecture: 127 (20.3%)
+  amd64: 82/464 attempted
+     165  unsupported operand form
          e.g. /usr/local/go/src/cmd/asm/internal/asm/testdata/386enc.s
+     109  instruction not encodable
+         e.g. /usr/local/go/src/cmd/asm/internal/asm/testdata/386.s
 ...
 ```
 
@@ -447,6 +461,7 @@ version control.
 | `0` | success |
 | `1` | a failure the program detected: a parse or assembly error, an error-severity lint diagnostic, a mismatch in `verify`, a file that cannot be read |
 | `2` | the arguments were wrong: a missing or extra argument, an unknown command or format, an invalid `--map` pair |
+| `3` | `debug --timeout` killed the debuggee |
 
 ## Examples
 
@@ -468,5 +483,5 @@ gasm asm --format goobj -p example.com/kernel -o kernel.o kernel_amd64.s
 Find which labels a failing kernel reaches, headlessly:
 
 ```sh
-gasm debug --func decodeBlockAVX2 --cover --script cmds.txt --timeout 30s kernel_amd64.s
+gasm debug --func decodeBlockAVX2 --cover --timeout 30s kernel_amd64.s
 ```

docs/DEVELOPMENT.md

@@ -6,9 +6,15 @@ Repository: [sourcedock.dev/petrbalvin/gasm-devkit](https://sourcedock.dev/petrb
 
 - **Go** 1.27.1, the exact version the `go` directive in `go.mod` declares
 - **just**, the command runner; every task below is a just recipe
+- **A C compiler** (`gcc`): `just race` runs the suite under the race detector,
+  which needs cgo
+- **Perl**: the `test`, `fmt-check`, `install-man` and `uninstall-man` recipes
+  are Perl programs
+- **`gzip`**: `install-man` compresses the man pages with it
 - A Linux host on amd64, arm64, riscv64 or loong64: `gasm debug` needs ptrace
   and the JIT checks of `gasm verify` need executable memory
-- No external dependencies beyond the Go toolchain
+- **`golang.org/x/arch`**, the one module dependency, which the Go toolchain
+  fetches; nothing else sits outside the standard library
 
 ## Setup
 
@@ -25,8 +31,9 @@ Every recipe in the `justfile`, and what it does.
 
 | Recipe | What it does |
 |---|---|
+| `default` (bare `just`) | prints the recipe list (`@just --list`) |
 | `just build` | compiles `bin/gasm` with `CGO_ENABLED=0` and stripped symbols; zero errors and zero warnings |
-| `just test` | the test gate: the suite with `-count=1`, the coverage profile and the 80 % floor |
+| `just test` | the test gate: the suite with `-count=1`, the coverage profile and the 80 % floor, then the CLI and debugger tests outside the profile |
 | `just race` | the same suite under the race detector; the expensive one, so it runs once, inside `gates` |
 | `just unit [packages] [run]` | fast, cached, scoped run for iterating: no race and no coverage, so an unchanged package reports instantly |
 | `just fuzz <target> <pkg> [fuzztime]` | time-boxed fuzz of one target; the package is required, because `go test -fuzz` refuses more than one |
@@ -36,8 +43,10 @@ Every recipe in the `justfile`, and what it does.
 | `just vet` | both static gates: `go vet` and `go fix -diff` |
 | `just gates` | `build`, `fmt-check`, `vet`, `test` and `race`, in that order: the definition of done |
 | `just clean` | removes the build artefacts, `bin/` and `coverage.out` |
-| `just install` | builds, then copies the binary into `bindir` (`~/.local/bin`); `gasm debug` needs an installed binary, because it spawns the debuggee from `$PATH` |
+| `just install` | builds, then copies the binary into `bindir` (`~/.local/bin`) |
 | `just uninstall` | removes the installed binary from `bindir` |
+| `just install-man` | installs the man pages under `docs/man` into `~/.local/share/man/man1` (`MANDIR` overrides), gzip-compressed; not a gate |
+| `just uninstall-man` | removes the installed man pages |
 | `just run` | runs the CLI with `go run -buildvcs=true`; the recipe takes no arguments, so flags go through the package instead |
 | `just dev` | the same as `run`; the project has no watcher to add |
 | `just gen` | regenerates the `arch` instruction tables from the Go toolchain source; not a gate |
@@ -53,9 +62,18 @@ go test -count=1 -timeout 10m -coverprofile=coverage.out \
 The suite runs over the logic packages (`-count=1`, so no cached pass
 counts): arch, asm, ast, disasm, format, lexer, lint, lsp, parser,
 token, verify. `debug` traces a live process and `cmd/gasm` is thin CLI
-glue, so both sit outside the sweep, and a thin `cmd/` in it would drag
-the coverage total under the floor. The floor fails if the total is
-below 80 %.  CI runs the same command with the same ten-minute bound, so
+glue, so both sit outside the profile sweep, and a thin `cmd/` in it
+would drag the coverage total under the floor. Their tests still run, in
+a second invocation without a profile:
+
+```sh
+go test -count=1 -timeout 10m ./cmd/... ./debug/...
+```
+
+That covers the CLI's exit codes and the guard that compares the manual
+pages with the binary's own help, and the debugger's architecture-neutral
+units. The floor fails if the total is below 80 %.  CI runs the same two
+commands with the same ten-minute bound, so
 the number is the same everywhere.
 
 ### `just run`
@@ -129,7 +147,8 @@ therefore the fastest way to a green pipeline.
 Releases are cut by merging `development` into `main` and tagging `vX.Y.Z`,
 which triggers the release workflow: it builds the portable Linux targets,
 takes the notes from the matching `CHANGELOG.md` section and uploads the
-assets.
+assets.  `SECURITY.md` carries the supported-versions table, so that table
+moves with the release; the pipeline refuses a tag the policy does not name.
 
 The version is never injected. `gasm --version` prints what the
 toolchain recorded in the build information: the tag on a tagged

docs/man/gasm-asm.1

@@ -1,4 +1,4 @@
-.TH GASM-ASM 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM-ASM 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm-asm \- assemble Plan 9 assembly without the Go toolchain
 .SH SYNOPSIS
@@ -20,13 +20,24 @@ flag selects what is written:
 self-consistent image;
 .B elf
 emits a relocatable object (.text/.data sections, a symbol table and
-one PC32 relocation per static-symbol reference) that links with the
+one relocation per static-symbol reference, in the architecture's own
+form: R_X86_64_PC32 on amd64, R_AARCH64_*, R_RISCV_* or R_LARCH_* on the
+others) that links with the
 system toolchain;
 .B goobj
 emits the Go toolchain's own object format, which cmd/link consumes
 directly (it requires
 .BR \-p ,
-the package path, and the installed Go toolchain).
+the package path, and the installed Go toolchain: the object preamble is
+captured from
+.B go tool asm
+and the format version from
+.BR "go version" ).
+.PP
+.B raw
+and
+.B elf
+need no toolchain at all.
 .PP
 Framed functions receive the stack-split guard and the trailing
 morestack block, byte-identical to the toolchain's output, so split
@@ -51,10 +62,10 @@ Exits 0 on success, 1 when parsing or assembly fails, and 2 on a usage
 error.
 .SH EXAMPLES
 .nf
-gasm asm \-o hello.bin hello_amd64.s               raw image
-gasm asm \-\-format elf \-o k.o k.s                 linkable ELF object
-gasm asm \-\-format goobj \-p pkg/path \-o k.o k.s   Go object for go build
-gasm asm \-GOARCH amd64 cpu_x86.s                  arch override
+gasm asm \-o hello.bin hello_amd64.s                      raw image
+gasm asm \-\-format elf \-o k.o k_amd64.s                  linkable ELF object
+gasm asm \-\-format goobj \-p pkg/path \-o k.o k_amd64.s   Go object for go build
+gasm asm \-GOARCH amd64 cpu_x86.s                         arch override
 .fi
 .SH SEE ALSO
 .BR gasm (1),

docs/man/gasm-audit-instructions.1

@@ -1,4 +1,4 @@
-.TH GASM-AUDIT-INSTRUCTIONS 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM-AUDIT-INSTRUCTIONS 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm-audit-instructions \- diff the encoder against the Go toolchain, or measure a corpus
 .SH SYNOPSIS
@@ -8,12 +8,17 @@ Compare the gasm encoder for the given architecture (default amd64)
 against
 .B go tool asm
 and print the diff: superset encodings (gasm-only, shippable via
-.BR "gasm asm \-\-format goobj" ),
-known-but-unencodable names (the backlog) and go-only names (feature
-gaps).  The Go side is probed black-box with a battery of bare
-mnemonics, so the audit tracks whatever toolchain
+.BR "gasm asm \-\-format goobj" )
+and known-but-unencodable names (the backlog).  The Go side is probed
+black-box one bare mnemonic at a time, so the audit tracks whatever
+toolchain
 .B go env GOROOT
-provides.
+provides; the gasm side answers from the encoder table on amd64 and from
+trial assembly over a battery of operand shapes elsewhere.  Names
+.B go tool asm
+knows and gasm does not cannot be enumerated by probing, because Go's
+table is visible only through names already in the gasm table; the report
+closes with a note saying so rather than listing them.
 .PP
 With
 .BR \-\-corpus ,

docs/man/gasm-debug.1

@@ -1,4 +1,4 @@
-.TH GASM-DEBUG 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM-DEBUG 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm-debug \- interactive source-level debugger for JIT-assembled functions
 .SH SYNOPSIS
@@ -17,14 +17,16 @@ runs to completion with a breakpoint on every instruction and reports
 which executed and how often, the label-level coverage view.
 .SH REPL COMMANDS
 .TP
-.B break \fIlabel|addr\fR [\fBif \fIreg op val\fR]
-Set a breakpoint, optionally conditional on a register comparison
-(register against register or immediate).
+.B break \fIlabel|addr|line\fR [\fBif \fIreg op val|reg|*addr\fR], b
+Set a breakpoint at a label, an address or a source line number, optionally
+conditional on a register comparison: against a constant, against another
+register, or against the 8-byte word at
+.BR *addr .
 .TP
-.B delete \fIlabel|addr\fR
+.B delete \fIlabel|addr\fR, d
 Remove a breakpoint.
 .TP
-.B info break
+.B info break, info breakpoints, info b
 List all breakpoints.
 .TP
 .BR step " [" n ], " s
@@ -98,10 +100,12 @@ Run REPL commands from a file (one per line) and exit; - reads stdin.
 .TP
 .B \-timeout \fIduration\fR
 Kill the debuggee after this duration (e.g. 30s); for headless --script
-runs.
+runs; a timeout exits 3.
 .SH EXIT STATUS
-Exits 0 when the scripted session completes and 1 when the debuggee
-crashes or a check fails; the debugger is Linux-only.
+Exits 0 when the scripted session completes, 1 when the debuggee crashes
+or a check fails, and 3 when
+.B \-\-timeout
+kills the debuggee; the debugger is Linux-only.
 .SH EXAMPLES
 .nf
 gasm debug \-\-func name k.s

docs/man/gasm-diff.1

@@ -1,4 +1,4 @@
-.TH GASM-DIFF 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM-DIFF 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm-diff \- compare the machine code of two assembly files
 .SH SYNOPSIS
@@ -28,7 +28,7 @@ differs; a usage error exits 2.
 .SH EXAMPLES
 .nf
 gasm diff hello_amd64.s hello_amd64.s
-gasm diff \-\-map wideCopyAVX2=wideCopyAVX512 avx2.s avx512.s
+gasm diff \-\-map wideCopyAVX2=wideCopyAVX512 avx2_amd64.s avx512_amd64.s
 .fi
 .SH SEE ALSO
 .BR gasm (1),

docs/man/gasm-dis.1

@@ -1,4 +1,4 @@
-.TH GASM-DIS 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM-DIS 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm-dis \- disassemble machine code to instruction text
 .SH SYNOPSIS
@@ -28,7 +28,7 @@ Exits 0 on success, 1 when assembly or decoding fails, and 2 on a usage
 error.
 .SH EXAMPLES
 .nf
-gasm dis k.s                          assemble, then list each function
+gasm dis k_amd64.s                    assemble, then list each function
 gasm dis \-a amd64 \- < dump.bin        disassemble raw bytes from stdin
 .fi
 .SH SEE ALSO

docs/man/gasm-fmt.1

@@ -1,4 +1,4 @@
-.TH GASM-FMT 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM-FMT 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm-fmt \- canonicalise the formatting of Plan 9 assembly sources
 .SH SYNOPSIS
@@ -41,6 +41,13 @@ List files whose formatting differs from gasm's.
 .TP
 .B \-w
 Write the result to the source file.
+.SH EXIT STATUS
+Exits 0 on success, 1 when a path cannot be read or written, and 2 on a
+usage error (combining
+.B \-l
+and
+.BR \-d ,
+or an unknown flag).
 .SH EXAMPLES
 .nf
 gasm fmt                                reformat every .s below here

docs/man/gasm-lint.1

@@ -1,4 +1,4 @@
-.TH GASM-LINT 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM-LINT 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm-lint \- run the static checks over assembly files
 .SH SYNOPSIS
@@ -33,7 +33,11 @@ The function can fall off its end without a terminator.
 TEXT flags are used without including textflag.h.
 .TP
 .B abi-argsize
-The declared frame or argument size disagrees with the
+The declared argument area (the
+.I \-args
+part of
+.IR $frame\-args )
+disagrees with the
 .B //\ function
 signature.
 .TP
@@ -52,7 +56,8 @@ FUNCDATA and PCDATA indices are malformed.
 A label no jump reaches.
 .TP
 .B invalid-textflag
-A TEXT flag combination the toolchain rejects.
+An unknown TEXT or GLOBL flag, reported one flag at a time; numeric flags
+are accepted as textflag.h constants.
 .TP
 .B stack-imbalance
 The function does not restore the stack pointer on every path.
@@ -61,11 +66,18 @@ The function does not restore the stack pointer on every path.
 An operand register has the wrong width for the instruction.
 .TP
 .B abi0-register-args
-A call passes arguments in registers where ABI0 expects the stack
-frame.
+A function whose
+.B //\ function
+parameters are never read from their
+.IR name+offset(FP)
+frame slots, which usually means the body takes its arguments from
+registers instead.
 .TP
 .B nonportable-register-name
-A register spelling that does not exist on the target architecture.
+An amd64 register alias gasm accepts but
+.B go tool asm
+rejects (the RAX/EAX family); the canonical spelling is named in the
+diagnostic.
 .TP
 .B unencodable-instruction
 The mnemonic is known to the table but the encoder cannot assemble it

docs/man/gasm-lsp.1

@@ -1,4 +1,4 @@
-.TH GASM-LSP 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM-LSP 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm-lsp \- run the Plan 9 assembly language server
 .SH SYNOPSIS

docs/man/gasm-parse.1

@@ -1,4 +1,4 @@
-.TH GASM-PARSE 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM-PARSE 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm-parse \- parse an assembly file and report syntax errors
 .SH SYNOPSIS

docs/man/gasm-profile.1

@@ -1,4 +1,4 @@
-.TH GASM-PROFILE 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM-PROFILE 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm-profile \- show the basic-block structure of functions
 .SH SYNOPSIS
@@ -6,9 +6,10 @@ gasm-profile \- show the basic-block structure of functions
 .SH DESCRIPTION
 Show the basic-block structure of functions in an assembly file: each
 function's labels, their offsets, and the block boundaries.  This is
-the static structure; for runtime execution counts, use
-.BR "gasm verify \-fuzz" ,
-which exercises the code paths.
+the static structure; for runtime execution counts use
+.BR "gasm debug \-\-cover" ,
+and for input coverage
+.BR "gasm verify \-\-fuzz" .
 .SH EXIT STATUS
 Exits 0 on success and 1 when the file cannot be assembled.
 .SH SEE ALSO

docs/man/gasm-scaffold.1

@@ -1,4 +1,4 @@
-.TH GASM-SCAFFOLD 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM-SCAFFOLD 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm-scaffold \- generate a differential test skeleton for a kernel file
 .SH SYNOPSIS

docs/man/gasm-tokens.1

@@ -1,4 +1,4 @@
-.TH GASM-TOKENS 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM-TOKENS 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm-tokens \- print the lexical token stream of an assembly file
 .SH SYNOPSIS

docs/man/gasm-verify.1

@@ -1,4 +1,4 @@
-.TH GASM-VERIFY 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM-VERIFY 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm-verify \- JIT-assemble a file and run dynamic checks against it
 .SH SYNOPSIS
@@ -20,8 +20,7 @@ With
 each function is called with sentinel values in the registers the Go
 ABI fixes across calls (the frame pointer and the goroutine pointer)
 plus a canary below SP; violations are reported.  JIT-based checks run
-when the host matches the file's architecture (all but loong64, which
-is ground-truth only for now).
+when the host matches the file's architecture, on all four architectures.
 .PP
 With
 .BR \-fuzz ,
@@ -46,7 +45,8 @@ a single function is invoked with user-supplied buffers
 .RB ( \-buf )
 instead of the smoke/abi/fuzz sweeps.  Useful for partial functions
 (e.g. decoders) that crash on random input but should succeed on valid
-data.
+data.  The function named must be NOSPLIT: a function with a stack frame
+is refused with a diagnostic and exits 1.
 .PP
 With
 .B \-save\-corpus
@@ -74,7 +74,7 @@ Buffer spec for -call: name:size:pattern[,name:size:pattern] where
 pattern is zero, ones, seq, or hex.
 .TP
 .B \-call \fIname\fR
-Call a single function with -buf instead of the sweeps.
+Call a single NOSPLIT function with -buf instead of the sweeps.
 .TP
 .B \-fuzz
 Differential fuzz: JIT both the gasm and the go-tool-asm versions and
@@ -108,8 +108,8 @@ a file that cannot be assembled exits 1 and a usage error exits 2.
 .SH EXAMPLES
 .nf
 gasm verify \-\-call add \-\-args a=2,b=3 hello_amd64.s
-gasm verify \-\-ground\-truth k.s
-gasm verify \-\-fuzz \-n 500 k.s
+gasm verify \-\-ground\-truth k_amd64.s
+gasm verify \-\-fuzz \-n 500 k_amd64.s
 .fi
 .SH SEE ALSO
 .BR gasm (1),

docs/man/gasm.1

@@ -1,4 +1,4 @@
-.TH GASM 1 "2026-09-19" "gasm 0.33.0" "User Commands"
+.TH GASM 1 "2026-09-19" "gasm" "User Commands"
 .SH NAME
 gasm \- developer tooling for Go's Plan 9 assembler
 .SH SYNOPSIS
@@ -17,11 +17,15 @@ bundles a lexer, parser, formatter, linter, standalone assembler and
 language server for Plan 9 assembly into one self-contained binary.  It
 serves two purposes: it brings developer tooling to the
 .I .s
-files of Go programs, and it assembles Plan 9 assembly without the Go
-toolchain at all, to raw images, linkable ELF objects with DWARF5 debug
-sections, or the Go toolchain's own GOOBJ format, which
+files of Go programs, and it assembles Plan 9 assembly to raw images or
+linkable ELF objects with DWARF5 debug sections without the Go toolchain at
+all, plus the Go toolchain's own GOOBJ format, which
 .B go build
-consumes directly.
+consumes directly.  GOOBJ is the one format that needs the toolchain
+installed: the object preamble is captured from
+.B go tool asm
+and the format version from
+.BR "go version" .
 .PP
 Four architectures are covered: amd64 (including VEX/AVX2 and
 EVEX/AVX-512), arm64, riscv64 (RV64IMAFDC and RVC) and loong64.  The
@@ -82,7 +86,8 @@ Show the command overview.
 Print the version the toolchain recorded at build time.
 .SH EXIT STATUS
 Exits 0 on success, 1 when a command fails, and 2 on a usage error.  An
-unknown command exits 2.
+unknown command exits 2; \fBgasm debug\fR exits 3 when \-\-timeout kills
+the debuggee.
 .SH SEE ALSO
 .BR gasm\-asm (1),
 .BR gasm\-fmt (1),

format/format.go

@@ -312,7 +312,7 @@ func spaceBetween(prev, cur token.Token) bool {
 		return false
 	case token.Comma:
 		return false
-	case token.Star, token.Plus, token.Minus, token.Slash:
+	case token.Star, token.Plus, token.Minus, token.Slash, token.Pipe:
 		return false
 	case token.LShift, token.RShift, token.Arrow, token.At:
 		return false
@@ -328,7 +328,7 @@ func spaceBetween(prev, cur token.Token) bool {
 		}
 	}
 	switch prev.Kind {
-	case token.LParen, token.Star, token.Plus, token.Minus, token.Slash:
+	case token.LParen, token.Star, token.Plus, token.Minus, token.Slash, token.Pipe:
 		return false
 	case token.Dollar:
 		return false

format/format_test.go

@@ -85,7 +85,7 @@ func TestBlankLines(t *testing.T) {
 		"TEXT ·f(SB), NOSPLIT, $0\n" +
 		"first:\n" + // first label: no blank after TEXT
 		"XORQ AX, AX\n" +
-		"JMP next\n" + // unlabeled glue: fmt inserts a blank before next:
+		"JMP next\n" + // unlabelled glue: fmt inserts a blank before next:
 		"next:\n" +
 		"stacked:\n" + // stacked labels share an address: no blank between
 		"INCQ AX\n" +
@@ -143,6 +143,7 @@ func TestOperandSpacing(t *testing.T) {
 		"swin_base+0(FP)": "swin_base+0(FP)",
 		"mask24<>(SB)":    "mask24<>(SB)",
 		"·idx16+0(SB)/4":  "·idx16+0(SB)/4",
+		"NOSPLIT|DUPOK":   "NOSPLIT|DUPOK",
 	}
 	for in, want := range cases {
 		toks := lexOperands(in)
@@ -152,6 +153,36 @@ func TestOperandSpacing(t *testing.T) {
 	}
 }
 
+// TestFlagListRoundTrip pins the '|' flag separator and the <ABIInternal>
+// marker through a full format pass: the bars the Go toolchain requires and
+// the ABI bracket must survive byte for byte, on TEXT and GLOBL alike.
+func TestFlagListRoundTrip(t *testing.T) {
+	for _, in := range []string{
+		"TEXT ·f(SB), NOSPLIT|NOFRAME|DUPOK, $0\n\tRET\n",
+		"TEXT ·foo<ABIInternal>(SB), NOSPLIT, $-0-24\n\tRET\n",
+		"GLOBL ·mask(SB), RODATA|NOPTR, $8\n",
+	} {
+		if got := Source(in); got != in {
+			t.Fatalf("flag list did not round-trip:\n--- got ---\n%q\n--- want ---\n%q", got, in)
+		}
+	}
+}
+
+// TestCRLFInputIsNormalisedToLF checks that a CRLF file comes out with
+// uniform LF endings: a // comment must not carry its line's trailing \r
+// into the output.
+func TestCRLFInputIsNormalisedToLF(t *testing.T) {
+	in := "// func f()\r\nTEXT ·f(SB), NOSPLIT, $0\r\nRET\r\n"
+	want := "// func f()\nTEXT ·f(SB), NOSPLIT, $0\n\tRET\n"
+	got := Source(in)
+	if got != want {
+		t.Fatalf("CRLF formatting mismatch:\n--- got ---\n%q\n--- want ---\n%q", got, want)
+	}
+	if strings.Contains(got, "\r") {
+		t.Fatalf("output still contains CR: %q", got)
+	}
+}
+
 // lexOperands lexes a single operand string and drops the EOF token.
 func lexOperands(s string) []token.Token {
 	toks := lexer.Tokenize(s)