Repository navigation
feat(minzoned,minvmd,minimal): one box-name service for a Mac's users, admitting a group - #2976
bryan-minimal wants to merge 10 commits into
Conversation
|
Important Draft PR not reviewedDraft PRs are not automatically reviewed by default.
To automatically review draft PRs, update your CodeRabbit configuration: reviews:
auto_review:
drafts: true
|
|
Lab prepush on anvil for this commit (6a4e81c on PR 1; job 01828, CI's commands on the box): fmt, clippy |
Spec lint
Advisory. None of this blocks the merge; the review decides. Advisory, and never a merge gate. Linter: |
b685126 to
b3d62a1
Compare
…, admitting a group `minzoned --admit-group GROUP`: the installed service admits, besides its own uid, root and every member of the group, judged on the peer's uid from the kernel before a byte of it is read (getgrouplist, the primary group and every supplementary one, with the buffer grown on truncation). A node is the hello's node id qualified with that uid, so another user speaking the same id is another node: nobody can replace or release another user's rows by naming their daemon, a clash between them is the ordinary first-publisher clash with the holder named, uid included, and the service keeps no state across a restart. The refusal a non-member reads names their account and the one command that admits them. `min finalize-install --show` knows such a shared service: the unit's `--admit-group`, the socket expected to be the group's (0660, the group's write bit) and the service account's, not the operator's; an operator outside the group is told the way in. The step never replaces the shared service, for a member or root either: over a custody failure or a protocol mismatch it is unavailable, with the package that installed the service named as the remedy, and `--undo` is refused over a unit that admits a group. With no user daemon reporting a port, the names item judges by the port the host's resolver hook names, when the service answers there. The macOS system package (next) runs the service this way under a role account. Spec 18's open question on several users of one host, option 2. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
…nd caps each user The four things the pre-PR read of #2976 found, and the smaller ones: - A group member is judged on the connection's own thread; the accept loop judges only what needs no lookup (the own uid, root, every peer of a single-operator answerer). On macOS membership asks the membership API (nested groups, more than sixteen groups), with getgrouplist behind it. - The shared service caps each user: 32 open channel connections, a quarter of the box range. A single-operator answerer caps nothing. - A box name stays its last user's for the answer TTL after its row goes, as an address does, so a reconnect never loses a name to another member. Across a service restart nothing is remembered; spec 18 says so. - The CLI's `--undo` and reinstall guards fail closed on a unit file that is there but not text (a binary plist, an unreadable file), naming the file. - `--admit-group` is read from the unit's program arguments, not anywhere in the file. A refusal names another user's node by uid, never by its state directory. The add-to-group line is the service's, by platform. - The admission test reads the account's groups, not the process's, and holds under root. Misplaced doc comments sit on their items. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Linux clippy (-D warnings) refuses the u32::try_from of a gid_t as a useless conversion; macOS's int entries still go through try_from. Found by the acceptance farm's Linux gate (j-be5b78a640086ce8).
…s were no-ops Linux clippy (-D warnings) refuses them as explicit_auto_deref; macOS's clippy let them through. Found by the farm's Linux gate (j-8665ac64ae4e3ac8).
A poisoned seat count is recovered, not expected; the plist's program arguments are read with split_once, not byte slices; the last unit path by last(). Found by the farm's Linux gate (j-182b311eb19bde37).
…not take another user's The answerer compared published names in a canonical form that strips one root dot, and the view strips one more when it holds a row. A member who published `web.min.internal..` passed every rule as a new name (not reserved, not held, not in quarantine), and the fold then replaced the row of `web.min.internal` with theirs: another user's box name, or `host.min.internal`, answered at an address the publisher chose. A row whose canonical name is not in its final form (it still ends in a dot, or carries an empty label) is refused at publish, and the fold skips such a row on its own account. The new test failed before the change with the second user's row held. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
On the shared service one user's nodes may hold a quarter of the box range. Three ways of asking for an address did not count against it: - `allocate` with an address to keep treated a free address the caller named as the box's own address coming back, and skipped the cap; - a claim under a name that already held some address skipped it, so one name could claim address after address; - node addresses are all kept by one name, so the second onward were free. One member with one connection could hold the whole range, and no other user could start a published box. The cap now applies to every address except the one this exact holder already holds or has in its quarantine. The new test handed one user 128 addresses against a share of 64 before the change. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
A name needs no address of the box range (a row may answer at the host loopback), so the per-user address cap bounded nothing here: one member could hold names by the tens of thousands over their connections, each a name no other member can use, and every publish compared each of its rows with every held row under the lock the lookups take (review finding B-3). On the shared service one user's nodes now hold at most four names for each address of their share, counted over all their connections. The cap is judged before any rule that reads the held rows, so a publish far past it costs one refusal a row. A single-operator answerer caps nothing. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
…og, and ends on a panic Three things a member of the admitted group could lean on (review findings B-5, B-6, B-7): - A reply to a peer that stopped reading had no bound: the write held the connection's thread and its seat for as long as the peer liked, and a refusal written on the accept loop could hold the loop. Every accepted connection now has a write timeout, the reply timeout the client side already reads under. - A publish wrote one warn line for each refused row, and each allocate and release a line of its own, at whatever rate the member sent them. A publish's refusals are one line now (the count, the first names, the first reason; the reply still names every row), and one connection's requests write at most 32 lines in 10 s, with the number left out reported once. - A panic on one thread left the process running with a poisoned table lock or no answering thread, which a service manager reads as healthy. minzoned's service now ends on any panic, after the panic's message; it keeps no state, and launchd or systemd starts it again. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
… account holds A node daemon trusted the channel socket by its path. Where the path's directory is another user's to make (the interim's /tmp/minimal-<uid> fallback on a Linux host with no XDG_RUNTIME_DIR), that user could listen there, be handed the node's box names, and say what addresses they hold. The node now asks the kernel who holds the listening end before it writes a byte: root (launchd and systemd make an installed service's socket; a package install measured uid 0, pid 1), its own account, or the owner of the socket's node when the directory is root's and not writable by group or other. Anyone else is refused with PermissionDenied, which the acquisition loop surfaces and never takes for a channel that is nobody's. Review finding F3 (low). Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
4b1222f to
bfd4de9
Compare
minzoned --admit-group GROUP: the installed service admits, besides itsown uid, root and every member of the group, judged on the peer's uid
from the kernel before a byte of it is read (getgrouplist, the primary
group and every supplementary one, with the buffer grown on truncation).
A node is the hello's node id qualified with that uid, so another user
speaking the same id is another node: nobody can replace or release
another user's rows by naming their daemon, a clash between them is the
ordinary first-publisher clash with the holder named, uid included, and
the service keeps no state across a restart. The refusal a non-member
reads names their account and the one command that admits them.
min finalize-install --showknows such a shared service: the unit's--admit-group, the socket expected to be the group's (0660, the group'swrite bit) and the service account's, not the operator's; an operator
outside the group is told the way in. The step never replaces the shared
service, for a member or root either: over a custody failure or a protocol
mismatch it is unavailable, with the package that installed the service
named as the remedy, and
--undois refused over a unit that admits agroup. With no user daemon reporting a port, the names item judges by the
port the host's resolver hook names, when the service answers there.
The macOS system package (next) runs the service this way under a role
account. Spec 18's open question on several users of one host, option 2.
Context
Second of three stacked PRs for the macOS system install (gominimal/inbox#1179); #2975 has merged, so this is the base of the stack. Spec 18 (
docs/specs/18-spec-box-networking.md) leaves the question of several users of one host open and lists the options; this is option 2: one box-name service for the Mac, admitting a group, with a node keyed by its id and the peer's uid. The per-user service's single-uid rule is unchanged; nothing changes on Linux.Proof
Three review rounds on the minfarm found and fixed, in order: a bindings file (removed; the pair keying replaced it), a takeover through
finalize-installby a group member, the ERANGE handling, the refusal wording, the mode check. The design, probes and rounds are in the farm'sdocs/research/box-name-service-users.md(gominimal/minfarm). minimal's Linux PR gates reproduced on the farm's Linux lane (the first run caught a getgrouplist buffer type that isinton macOS andgid_ton Linux); minvmd's tests on macOS (685); the lab prepush on anvil.The pre-PR review (2026-11-04), settled in the second commit
The four things the read found, and the smaller ones, are in
5f8f7cb6:mbr_check_membership(nested groups, more than sixteen), withgetgrouplistbehind it. The admission test reads the account's groups, not the process's, and holds under root.--showoffer nothing and--undorefuse, both naming the file and theplutilline that reopens it.--admit-groupis read from the unit's program arguments (the plist'sProgramArgumentsarray, the unit'sExecStart=), not from anywhere in the file.--showagree.Proof of the second commit
cargo nextest run -p minimal --libin a box): 702 passed, 1 skipped (j-4f06879a0ed6efb6).cargo nextest run -p minvmd --libon a Mac: 689 passed. Clippy clean on the three crates.dseditgroupline; a member published a name and went, root was refused it (another user's node (uid 501) released this name less than 15 s ago; it stays theirs for 14 s more), the member took it straight back; the 33rd connection of one user was refused with the count and the 32nd served;plutil -convert binary1on the plist made--showand--undorefuse naming the file, exit 1, andxml1reopened them. The package journey itself passed on the same build (j-dfb7a945fce76e81).Still to decide, not code: the package README's open questions (#2977).
Since the pre-PR review (rounds to 2026-11-14)
Rebased onto main. Later review rounds on the farm added:
getgrouplistentry is agid_ton Linux (caught by the farm's Linux lane), and the strict lints on the new lines.Proof on 2026-11-16: minimal's Linux PR gates on this branch in the farm's Linux lane, 13 of 13 steps; the package built on this branch passed 16 journeys in fresh macOS VMs (#2977 lists them).
🤖 Generated with Claude Code