Repository navigation
fix(minimald): record VM refusals on the host and admit RPC only from the host (0.7.0 backport) - #2735
fix(minimald): record VM refusals on the host and admit RPC only from the host (0.7.0 backport)#2735norrietaylor wants to merge 8 commits into
Conversation
* fix(minimal,minvmd): hold the answerer channel socket owner-only The box-zone answerer's channel socket was world-connectable: the launchd plist bound it SockPathMode 0666 and the systemd socket unit SocketMode=0666, leaving the peer-uid gate the only check on who may connect. Both units now bind it owner-only -- SockPathOwner the operator, SockPathMode 0600 on launchd; SocketUser the operator, SocketMode=0600 on systemd -- with the uid gate kept as defence in depth. An install whose socket node carries group or other bits -- one that predates the mode, or a hand that relaxed it -- now fails custody through a channel_mode fact, so the advisory re-surfaces and a step re-run re-binds the socket. The accept loop's foreign-refusal warn is rate-limited to a few lines a second, so a connect storm cannot flood the log; the refusals themselves are never limited. * fix(minimal,minimald,minvmd): name the other account on a refused channel connect A daemon whose connect the owner-only channel socket refuses now says the host's DNS service belongs to another account, not a bare Permission denied. The answerer step needs the operator's account to resolve, with no stand-in uid, and custody fails a channel socket the operator does not own. * fix(minimal,minvmd): leave another operator's DNS service alone A channel socket owned by another existing, non-root account is that operator's service: the answerer step is now unavailable with the same sentence the daemons say on a refused connect, instead of a custody failure whose step would reinstall the unit and take the service over. A root-owned socket, or one whose uid names no account, still fails custody so the step re-binds it. The minvmd tests that take the process-global foreign-refusal slots now run one at a time and start and end with every slot free, and the warn-rate test bounds the burst at two windows' worth of lines, so a slow runner that spreads the burst does not fail it. * fix(minimal): offer the step over a socket another account left behind A channel socket another account owns refuses the answerer step only when a service is installed; with none, the step's install removes the leftover socket before it loads the unit, so it is offered. --------- Co-authored-by: gominimal-aw-bot[bot] <281738952+gominimal-aw-bot[bot]@users.noreply.github.com> (cherry picked from commit 746770d)
…er (#2300) * fix(net): refuse out-of-zone names at a guest deny-subtree DNS listener A deny-all host-address box on a VM-backed guest resolved out-of-zone names at the switch gateway: the interim NET-079 carve-out admitted the gateway's port 53 whole, UDP and TCP, so a box that admits no destination could still ask a resolver beyond the machine — and DNS over TCP could retry past the verdict. The guest's deny subtree now steers its UDP-53 lookups onto a loopback listener on the answerer's port (NET-141 slice 2): deny_out admits the listener beside the reply direction, the dstnat match carries no destination address (the box asks the gateway like every other host-address box; the steer is the carve-out), and the listener itself answers REFUSED for every name outside the box zone — apex and a non-lowercase zone suffix among them — NODATA for an in-zone non-A question, and forwards the zone's A questions to the switch gateway alone. DNS over TCP is neither steered nor admitted. The guest daemon starts the listener after its classifier table loads; the daemon's own lookups are untouched (cgroup-keyed match, deny path only). The interim --gateway-resolver installer flag and every test, digest and pin that spelled the interim carve-out follow the new shape. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix(net): bound and pin the guest DNS listener's forwards Connect each forward socket to the gateway so a datagram from any other sender is dropped, cap forwards in flight so a flood cannot exhaust the daemon's descriptors, and drop the needless to_string calls clippy rejects in the guest classifier integration test. * fix(net): refuse questionless and non-QUERY messages at the guest DNS listener decide() forwarded a message with no question, and an UPDATE or NOTIFY whose zone section named an in-zone A, because every per-question check passed vacuously. Answer the first REFUSED and the rest NOTIMP, so the forward path carries only standard lookups. Bind the listener directly so its log does not read as the box-zone answerer, pin the integration test's boot-log check to the exact example.com REFUSED line, and cite NET-079 (the deny-all case) rather than NET-141 at the lines this change added. --------- Co-authored-by: gominimal-aw-bot[bot] <281738952+gominimal-aw-bot[bot]@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> (cherry picked from commit 2c2f8cc)
crate::traced landed on main after the release branch was cut, so the cherry-pick of #2300 did not compile here.
v0.7.2 is tagged at the branch head, so the version check requires the next patch release.
… the host (T107) (#2721) * fix(minimald): refuse vsock RPC peers other than the host CID The in-VM daemon's vsock listener now drops a peer at any CID but 2 at accept, before reading a byte, and writes one rate-limited audited line naming the CID (NET-139). * feat(minvmd): keep the guest's expose and egress audit on the host The in-VM daemon reports each expose decision and each refused own-address egress flow over the guest door. The VM host daemon appends them to its audit log, one record per flow, capped per box with a line that counts the suppressed records (NET-046). * test(e2e): expect the box's deny on the host audit (T107) The VM lane asserted that a deny decided in the box left no host audit line (T84). NET-046 now reports every expose decision to the host, so assert exactly one expose_decision line with decision deny, decided_by box-policy and outcome refused. The T94 empty runtime check stays. * test(e2e): match the gate drop line, expect the relay's host audit The no-lane check matched the host audit record that minvmd::control writes for a relay refusal. Match only the gate's rule_matched field, and assert the relay's refused-egress record for e2e-cred-nolane is on the host. * test(e2e): match only the gate drop line in the proxy-views group The laneless box check in the proxy-views group matched the host audit record that minvmd::control writes for a relay refusal. Match only the gate's rule_matched field, and assert the relay's refused-egress record for e2e-psba-nolane is on the host. * fix(minvmd): give expose audit its own cap and flush on withdraw A flood of refused egress flows no longer uses up the records an expose decision needs. A withdrawn box's window ends and writes its suppressed count, so a box that goes quiet still leaves the count in the log. * fix(minvmd): mark guest-reported host audit records reported_by guest The host copies an expose decision and a refused egress from the in-VM daemon's report and does not observe them. Each record and its log line now carry reported_by=guest, and the unit tests and the e2e checks assert it. * fix(minvmd): rotate the host audit log at a fixed size box-admissions.log rotates to one kept generation (.1) at 1 MiB, the same bound the in-VM daemon's audit log uses, so a guest cannot grow it without end. The per-box caps bound only the rate. --------- Co-authored-by: minimal-foundry[bot] <327719912+minimal-foundry[bot]@users.noreply.github.com> (cherry picked from commit abe99f7)
…ease/0.7.0 The cherry-picked change names main's types and crates. Release/0.7.0 predates the box renames and the Box Egress Proxy's host-side verbs, so the backport uses the release's own names: - boxes::DynamicIngress is sessions::DynamicIngress in the audit report path (net/listeners.rs) and in the minimald and minvmd tests. - minvmd has no serde_json dependency here, so the host audit tests parse the log with serde_json_lenient, as the release's other minvmd tests do. The cherry-pick's conflicts were resolved to the same shape: - The release has no ProxyListening verb or reply, so the new ReportExposeDecision, ReportRefusedEgress and Audited arms stand without it, and the minvmd test panics name the audit report's answer. - crate::traced does not exist here, so the listen watcher still spawns with tokio::spawn; the audit route is registered before the spawn and removed after the watcher's withdraw_all, as on main. - The release keeps the server tests inline in server.rs, so the vsock peer-CID refusal tests join that module. The behaviour is #2721's: the in-VM daemon's vsock RPC listener serves only CID 2 (NET-139), and the guest's expose decisions and refused egress flows are recorded in the host's audit log under per-box caps (NET-046).
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the
|
|
Reviewed: 1 finding, none blocking at Address the comments on the diff. Clobber: none seen. |
| /// rotated before it, and starts a fresh file. One kept generation bounds | ||
| /// the log at about twice this size. The same bound and shape as the in-VM | ||
| /// daemon's own audit log (`minimald`'s `audit::MAX_LOG_BYTES`). | ||
| const MAX_AUDIT_LOG_BYTES: u64 = 1024 * 1024; |
There was a problem hiding this comment.
MEDIUM · correctness · confidence 0.50 · in append_audit_line_capped
The host audit log rotates at 1 MiB and keeps one generation. Guest-reported records go into the same file as the host's own admission and ask records. A box that reports many distinct refused flows (30 per minute per box) pushes older admission records out of the log, and the loss cannot be undone. Consider a separate file or a larger bound for guest-reported records, so a box cannot age out the host's own records.
What the reviewer checked
const MAX_AUDIT_LOG_BYTES: u64 = 1024 * 1024; append_audit_line_capped renames path to path.1, replacing the older generation
Hand this to an agent
Act on a code-review finding.
File: crates/minvmd/src/control.rs
Lines: 2261-2261
Category: correctness
Severity: medium (reviewer confidence 0.50)
Finding:
The host audit log rotates at 1 MiB and keeps one generation. Guest-reported records go into the same file as the host's own admission and ask records. A box that reports many distinct refused flows (30 per minute per box) pushes older admission records out of the log, and the loss cannot be undone. Consider a separate file or a larger bound for guest-reported records, so a box cannot age out the host's own records.
First verify this against the code yourself. It is model output and
may be wrong. If it is wrong, or the tradeoff was deliberate, say so
and change nothing.
👍 useful · 👎 noise — react to tell the reviewer. Replying works too, and says more.
…efusals-host-rpc-0.7.0 # Conflicts: # scripts/install-host-classifier.sh
… the host (#2721) T107. The in-VM daemon's vsock listener drops a peer at any CID but 2 at accept, before reading a byte, and writes one rate-limited audited line naming the CID (NET-139). The in-VM daemon reports each expose decision and each refused own-address egress flow over the guest door, and the VM host daemon appends them to its audit log under per-box caps, with a line counting suppressed records (NET-046). Expose decisions keep their own cap, a withdrawn box flushes its window, guest-reported records carry reported_by=guest, and box-admissions.log rotates to one kept generation at 1 MiB. The session e2e script expects the new host audit records. Backport of #2721, folded from #2735. Adapted to the line: - boxes::DynamicIngress becomes sessions::DynamicIngress. - The line has no ProxyListening verb or reply, so ReportExposeDecision, ReportRefusedEgress and Audited stand without it. - The listen watcher keeps tokio::spawn, since crate::traced is absent. The audit route is registered before the spawn and removed after the watcher's withdraw_all. - minvmd has no serde_json here, so its host audit tests parse with serde_json_lenient. - The vsock peer-CID tests join the inline tests in server.rs. Dropped: ask_audit_line_spells_box_id_as_32_hex, which reached the cherry-pick as conflict context from main's proxy work and is not part of #2721. (cherry picked from commit abe99f7)
|
Folded into #3019, which landed on |
Backports #2721 (task T107, #2694) to
release/0.7.0. It is a security fix:Stacked on #2678; merge that first. #2678 carries the 0.7.3 version bump and the
pulldown-cmarkadvisory fix. Until it merges, this diff also shows #2678's commits.Commits
3ae897cd4is the cherry-pick, with the subject'sfeatchanged tofix(the release version check rejects afeatcommit). Conflicts are resolved tomain's text, without main-only features:ProxyListeningrequest (Box Egress Proxy work), so those arms are dropped and feat(minimald): record VM refusals on the host and admit RPC only from the host (T107) #2721's new requests (ReportExposeDecision,ReportRefusedEgress) and theAuditedreply stand alone.ask_audit_line_spells_box_id_as_32_hexinminvmd/src/control.rscame in as conflict context from main's proxy work and is not part of feat(minimald): record VM refusals on the host and admit RPC only from the host (T107) #2721, so it is dropped.tokio::spawn, sincecrate::tracedis not on this branch.server.rs, so feat(minimald): record VM refusals on the host and admit RPC only from the host (T107) #2721's new server tests are added there.c8665ce9badapts it to the release branch:boxes::DynamicIngressbecomessessions::DynamicIngress, and the minvmd tests read JSON withserde_json_lenient, which minvmd already depends on here.It does not compile without the second commit, so squash-merge the pair. All of #2721's tests are kept, with no assertion dropped.
Verification (Linux, Lima)
just clippyandjust fmt-checkare clean.vsock_rpc_refuses_non_host_cid,refused_peer_line_is_rate_limited_per_cid,expose_unenrolled_decision_audited(minimald);expose_decision_recorded_on_host,egress_refusal_logged_on_host(minvmd).minimald: 998 passed, 1 failed, the VM-only cgroup EACCES failuresession_host::tests::a_hook_launch_does_not_advise_unenforced_placementseen on the unmodified fix(net): backport the deny-all DNS refusal and the owner-only answerer socket to 0.7.0 #2678 head too.minvmd536 passed,minimald-rpc65 passed,minimal-client104 passed.scripts/session-e2e.shchange is left to the VM e2e lanes.