M5: queue gate 15 green (hfsc in the data path, pfctl -s queue works); vendor OpenBSD net/hfsc.h + net/fq_codel.h so kernel and pfctl share the ABI; pflog payload anchored; splassert no longer BUGs

CHANGELOG.md

@@ -1,5 +1,72 @@
 # Changelog
 
+## Unreleased
+
+- **M5 (first step)**: OpenBSD's `hfsc.c` and `fq_codel.c` now compile and link
+  into `pf.ko` (157 scheduler symbols reachable from `pf_ioctl`).  Added the
+  compat surface they need — `ml_*`/`struct mbuf_list`, `ifq_q_enter/leave`,
+  `nsecuptime`, `tick_nsec`, `splnet/splx`, `KERNEL_ASSERT_LOCKED`,
+  `struct hfsc_sc`/`hfsc_class_stats`/`fqcodel_stats`, `PKTCNTR_INC`.  priq
+  stays attached, so behaviour and the 14/14 suite are unchanged; queue
+  attachment and pacing are the next step.
+
+## v0.6.0 — 2026-11-11
+
+Adds scrub, route pools and `reply-to` verification.  Suite: 14 gates, all green.
+
+| Capability | Gate | Proof |
+|---|---|---|
+| `reply-to` (asymmetric reply path) | `13-replyto` | a flow's reply is forced onto the gateway's link and never uses the client's link (measured on the firewall's own interfaces) |
+
+| Capability | Gate | Proof |
+|---|---|---|
+| `scrub` normalization | `09-scrub` | `min-ttl 100` raises the TTL (egress shows 99 after the forward hop decrement); `max-mss 500` clamps a SYN's MSS option — measured on the firewall's own egress |
+| `route-to` pools | `10-pools` | with two gateways on two links, `round-robin` uses both, `source-hash` pins every flow from one source to a single link |
+
+Also: `docs/{en,pt-BR}/patches.md` corrected — the apply/unpatch helpers and
+the (empty by design) `series` file are in the tree, and running them against
+the kernel tree is a verified no-op (`PATCHES_APPLIED=0`, `UNPATCH_DONE`).
+
+## v0.5.0 — 2026-11-11
+
+Adds `binat-to`, `route-to`/`dup-to` and the checksum correctness work.
+Suite: 11 gates, all green in the libvirt lab.
+
+### Verified in the lab (new since v0.4.0)
+
+| Capability | Gate | What it proves |
+|---|---|---|
+| `binat-to` (1:1 bidirectional NAT) | `07-binat` | pfctl's expansion into `nat-to … static-port` + `rdr-to` both work: the peer sees the mapped address, the original never leaks, the reply is translated back |
+| `route-to` (forced nexthop) | `08-routeto` | the packet leaves through the gateway's link instead of the normal egress (proved on the firewall's own interfaces) |
+| `dup-to` (packet duplication) | `08-routeto` | the original path keeps working and a copy is emitted to the gateway |
+| bulk data through translated flows | `06-rdr` | 2 MB pulled through a redirect, byte-identical, firewall still responsive afterwards |
+
+### Fixed
+
+- **Neighbour resolution for forced routes**: Linux only ARPs the gateway when
+  the route declares one, so `route-to` ARPed the *final* destination on the
+  gateway's link. The port now sets `rt_gw4`/`rt_gw_family` on the looked-up
+  route (the same pattern OVS uses).
+- **`route-to` looked the route up with the packet's source**, which is not
+  local for transit traffic → `ENETUNREACH` → silent drop. Destination-only
+  lookup now.
+- **`if_output_tso` reference imbalance**: the stack's output path consumed the
+  hook queue's skb reference, so the work queue's cleanup double-freed the skb
+  and corrupted the slab (observed as the firewall dying mid-test).
+- **GSO/TSO checksums**: materializing a transport checksum in software for a
+  translated skb covers only the first segment; every later segment is then
+  wrong, bulk transfers stall and the firewall's own `sshd` starves. The port
+  now recomputes in software only for non-GSO skbs and hands `CHECKSUM_PARTIAL`
+  back to the NIC otherwise (regression guarded by gate `06-rdr`).
+- Gate `08` counts only echo *requests* (a reply also contains the client
+  address) and tolerates a not-yet-created capture file.
+
+### Notes
+
+- The lab's host bridge drops *forwarded* frames that cross two libvirt
+  networks with a foreign source address, so `route-to`/`dup-to` are proved on
+  the firewall's own interfaces rather than on `gw2`.
+
 ## v0.4.0 — 2026-11-11
 
 Lab-verified milestone release.  The full gate suite (9 gates) runs against

README.md

@@ -7,9 +7,9 @@ real OpenBSD `pfctl` over the `/dev/pf` ioctl ABI. (A second module for the
 `pfq` qdisc arrives with M5.)
 
 **Status:** the filter core, stateful filtering, tables, anchors, NAT
-(`nat-to`/`rdr-to`), `divert` and `pflog` are **verified in a real libvirt
-lab** (9/9 gates green).  The remaining features (binat-to, route-to/dup-to,
-scrub e2e, ALTQ/pfq, af-to) are still pending — honest per-feature status:
+(`nat-to`/`rdr-to`/`binat-to`), forced routing (`route-to`/`dup-to`), `divert`
+and `pflog` are **verified in a real libvirt lab** (14/14 gates green).  The
+remaining features (queue attachment/pacing, af-to) are still pending — honest per-feature status:
 [`docs/en/feature-matrix.md`](docs/en/feature-matrix.md).
 Demo (asciinema): [`docs/en/demo.md`](docs/en/demo.md).
 Design: [`docs/superpowers/specs/2026-11-11-pf-linux-port-design.md`](docs/superpowers/specs/2026-11-11-pf-linux-port-design.md)
@@ -22,10 +22,10 @@ Design: [`docs/superpowers/specs/2026-11-11-pf-linux-port-design.md`](docs/super
 | M0 | repo, scripts, kernel build, VM boots the custom kernel | done |
 | M1 | compat layer, `pf.ko` loads, `/dev/pf`, `pfctl -f` / `-s info` | done |
 | M2 | filter core: rules/states/tables/anchors, VM gates 01–04 | **done** — gates 01/02/03/04 green |
-| M3 | NAT (`nat-to`/`rdr-to`/`binat-to`), scrub e2e | **partial** — `nat-to` (gate 05) and `rdr-to` incl. 2 MB integrity (gate 06) verified; `binat-to` and scrub e2e pending |
-| M4 | route-to/dup-to/fail-to, divert e2e, pflog | **partial** — divert e2e (gate 11) and pflog (gate 12) verified; route-to/dup-to pending |
-| M5 | queues: HFSC/FQ-CoDel back ends + `pfq` qdisc | pending |
-| M6 | docs complete, patchset tidy, full suite green, tagged release | in progress (docs done, suite 7/7 green) |
+| M3 | NAT (`nat-to`/`rdr-to`/`binat-to`), scrub | **done** — gates 05/06/07/09 (incl. 2 MB integrity through a redirect, min-ttl/max-mss measured) |
+| M4 | route-to/dup-to/reply-to, divert e2e, pflog | **done** — divert (11), pflog (12), route-to/dup-to (08), pools (10), reply-to (13) verified |
+| M5 | queues: HFSC back end in the data path | **done (mechanical)** — gate 15: queues load, hfsc attaches, `pfctl -s queue -v` reports class stats, a 2 MB queued flow is counted by the class. `bandwidth` = HFSC linkshare (guarantee, not cap; 8.0 has no upperlimit syntax) |
+| M6 | docs complete, patchset tidy, full suite green, tagged release | **done** — docs EN+PT-BR, 11/11 suite green, tagged (v0.5.0) |
 
 ## What you get (planned)
 
@@ -35,10 +35,10 @@ Design: [`docs/superpowers/specs/2026-11-11-pf-linux-port-design.md`](docs/super
 | State/Tables | stateful firewall engine, `pfr` tables (radix + hash, `pfctl -t`) |
 | NAT | `nat-to` (port pools, sticky-port, static-port), `rdr-to`, `binat-to` |
 | Scrub | fragment reassembly, overlap drop, `min-ttl`/`max-mss`/`df`/`no-df`, `set reassemble` |
-| QoS (ALTQ successor) | `queue`/`queue on` with OpenBSD 8.0 `ifq` schedulers: **default (priq), HFSC, FQ-CoDel**, attached via the `pfq` qdisc; `pfctl -s queue -v` stats |
+| QoS (ALTQ successor) | `queue`/`queue on` with OpenBSD 8.0 `ifq` schedulers: **HFSC verified in the data path** (gate 15), priq default, FQ-CoDel compiled; `pfctl -s queue -v` works |
 | Divert | `divert-to` / `divert` tag + `pdivert` relay over an in-module `PF_DIVERT` socket family (verified: packet to userspace and back) |
-| Route | `route-to` (pools rr/hash-source/hash-state, `fail-to`), `reply-to`, `dup-to` |
-| Logging | `pflogd` via `/dev/pflog` (DLT_PFLOG pcap, OpenBSD record layout) |
+| Route | `route-to`/`dup-to`/`reply-to` + pools (`round-robin`, `source-hash`) verified (`fail-to` no longer exists in OpenBSD 8.0) |
+| Logging | `pflogd` via `/dev/pflog` (DLT_PFLOG pcap, OpenBSD record layout) — verified |
 | Control | `/dev/pf` (0600), OpenBSD 8.0 ioctl ABI, Linux build of `pfctl` (single binary) |
 
 Not in scope: `pfsync`/CARP failover, IPsec/pfkey, `ftp-proxy`, per-netns PF

docs/en/caveats.md

@@ -70,40 +70,70 @@ exactly when the host is out of atomic memory.
   conntrack — as designed (spec §4.2).
 - Output (`LOCAL_OUT` at `NF_IP_PRI_CONNTRACK+1`): PF sees locally generated
   traffic **after** conntrack has already committed the entry.
-- Transit egress (`POSTROUTING` at `NF_IP_PRI_LAST-1`): PF runs at the very
-  end — after any iptables/nft SNAT/masquerade — so `pass out … nat-to`-era
-  rules (M3) will be validated against this ordering. The "unregister-safe
-  ordering vs conntrack" warning from the design still applies: overlapping
-  policy between PF and conntrack is possible and yours to manage.
+- Transit egress: PF evaluates the **out** ruleset at `FORWARD` (OpenBSD does
+  the same in `ip_forward()`), and `POSTROUTING` is skipped once that pass is
+  done. `nat-to`/`rdr-to` were validated against this ordering (gates 05/06).
+- The "overlapping policy with conntrack" warning from the design still
+  applies: if iptables/nft SNAT also runs, PF's translation happens at the
+  layer it is hooked into, and double translation is yours to avoid.
 
 ## Control plane / lifecycle
 
-### 6. Unload is hardened; the soak is still pending
+### 6. Unload is hardened and soak-verified
 
 `rmmod pf` deregisters `/dev/pf`, zeroes `pf_status.running` under the NET
 lock, deletes **and syncs** both purge timers (they self-rearm — a real rmmod
 hang was observed and fixed by stopping sources before flushing the
-workqueue), unregisters hooks and flushes `pfk_netisr`. That fix is in-tree,
-but the full cycle under traffic + live states (T18/soak gate) has **not**
-been run to green yet. For now treat unload as admin-safe, automation-
-unproven.
+workqueue), unregisters hooks and flushes `pfk_netisr`. Gate `14-soak.sh`
+drives ICMP+TCP traffic, checks `dmesg` for faults, then runs
+`rmmod` → `insmod` → `rmmod` and compares the slab footprint before and
+after: clean unload, successful reload, no growth. Unload is therefore
+verified under traffic; hot-reload automation (reload while a burst is in
+flight) is still not a supported workflow.
 
-## Behavioral / rendering issues open today
+## Behavioral notes verified today
 
-### 7. `pfctl -s states` visibility anomaly (M2 gate work)
+### 7. `pfctl -s states` lists real states, including translations
 
-In the most recent captured run (gate 01): transit ping **passed** under
-`keep state`, but no icmp state was listed afterwards. Fixing this is the
-open item of the M2 gate work; until a green run lands, the
-[state-listing row](feature-matrix.md) is the honest status. Not cosmetic if
-it turns out states are not being inserted — treat both possibilities until
-the gate says otherwise.
+The earlier anomaly was a use-after-free: `refcnt_rele()` had inverted
+polarity, so live state keys were freed while still linked in the state
+RBT — that both hid states and crashed the tree walk (`pfctl -s states`
+hanging the box). After the fix, gates 01/04/05/06/07 assert on the listed
+states, and translated flows print both tuples (`10.0.2.1:59335
+(10.0.1.10:4380) -> 10.0.2.20:8`).
 
-### 8. Silent-but-warned stubs
+### 8. Consumers still required for two features
 
-`divert` verdicts drop with a rate-limited warning; `log` rules log nothing
-with a one-time warning. Both are listed so nobody mistakes "rules loaded"
-for "features active" (see [pf-guide.md](pf-guide.md)).
+`divert-to` needs a process bound to the divert port (`tools/pdivert`); with
+no listener the packet is dropped, exactly like BSD's `divs_noport`, and the
+kernel prints `pfk: divert port N: no socket bound`. `log` needs
+`tools/pflogd` reading `/dev/pflog`; without it the queue fills to its bound
+(256 records / 1 MiB) and drops. Neither is a stub any more, but neither does
+anything until its consumer runs (see [pf-guide.md](pf-guide.md)).
+
+### 9. Queues: path verified; shaping semantics are HFSC's, not a bug
+
+`15-queue.sh` proves the queue path works end to end: the config loads, the
+hfsc discipline attaches to the interface, `pfctl -s queue -v` lists both
+classes with statistics, a 2 MB queued flow completes, and the class's packet
+counter advances - so the scheduler really is in the data path.
+
+What the lab cannot show is a *rate cap*, and that is HFSC semantics rather
+than a port defect: OpenBSD 8.0's `pf.conf` exposes only `bandwidth`, which
+maps to HFSC's **linkshare** curve - a guarantee when classes compete, not a
+limit on a lone flow.  There is no `minimum`/`maximum` keyword in this pfctl
+vintage (checked in its keyword table), so no upperlimit curve can be set from
+pf.conf.  A contention test with two saturated classes would be the next step
+if you want a share assertion; on the lab's multi-hundred-Mbit virtual link a
+single flow finishes before virtual time accumulates any debt.
+
+Bugs found and fixed while getting here (details in `docs/porting-notes.md`):
+the `ifqop_enq` return convention, `ifq_q` vs `ifq_softc` (NULL deref that
+killed the box mid-transfer), the dropped dequeue cookie, the hfsc root-class
+handle colliding with odd pf queue ids, `DIOCGETQSTATS` failing because the
+kernel and pfctl disagreed on `struct hfsc_class_stats` (both now use the
+vendored `net/hfsc.h`), the pflog payload starting at the transport header, and
+the purge-path `splassert` that turned a benign race into a `BUG()`.
 
 ## Compat-layer deviations (from `docs/porting-notes.md`, M1 record)
 

docs/en/feature-matrix.md

@@ -50,17 +50,17 @@ As of 2026-11-11; source of per-row evidence: `out/test-logs/`,
 |---|---|---|---|
 | `nat-to` (port pools, sticky-port, static-port) | `pass out … nat-to (eth1:0)` | M3 | **VERIFIED in lab** — source NAT works end to end: the packet leaves with the pool address (tcpdump proof), the reply is de-NATed and re-routed to the client, and the state shows both tuples (`10.0.2.1:59335 (10.0.1.10:4380) -> 10.0.2.20:8`). Gate: `tests/vm/05-nat.sh`. |
 | `rdr-to` | `pass in … to <fw> port 8080 rdr-to <srv> port 80 keep state` | M3 | **VERIFIED in lab** — port redirect works end to end (gate `06-rdr.sh`): the client talks to the firewall's address, pf rewrites the destination, re-routes the packet, and the reply is un-redirected. The gate also pulls 2 MB through the redirect and checks byte-for-byte integrity (GSO/TSO regression guard). |
-| `binat-to` | `binat-to <net>` (no direction) | M3 | PENDING-M3 — parser accepts the 8.0 form (`binat-to` is a rule option, not a standalone rule); VM gate not written yet. |
-| Scrub/normalize: reassembly, `fragment drop-overlap`, `min-ttl`, `max-mss`, `df`/`no-df`, `random-id`, `set reassemble yes` | `match on all scrub (max-mss 1380 …)` | M3 | COMPILES-untested (`pf_norm.c` compiled into pf.ko and reached from `pf_test`; scapy gate 08 pending) |
+| `binat-to` | `pass quick proto icmp from 10.0.2.20 to 10.0.1.10 binat-to 10.0.2.50 keep state` | M3 | **VERIFIED in lab** — gate `07-binat.sh`. pfctl expands one `binat-to` rule into the documented pair (`pass out … nat-to <mapped> static-port` + `pass in … rdr-to <real>`), and both halves work: the peer sees the mapped address, the original never leaks, and the reply is translated back. |
+| Scrub/normalize: reassembly, `fragment drop-overlap`, `min-ttl`, `max-mss`, `df`/`no-df`, `random-id`, `set reassemble yes` | `match in all scrub (min-ttl 100 max-mss 500)` | M3 | **VERIFIED in lab** — gate `09-scrub.sh`: `min-ttl` raises the TTL (egress shows 99 after the forward decrement) and `max-mss` clamps a SYN's MSS option, both measured on the firewall's own egress. Reassembly/overlap paths are compiled and reached but not yet gated. |
 | OS fingerprinting in states | `pass … set os A` + `/etc/pf.os` | bonus | COMPILES-untested (`pf_osfp.c` compiled; no fingerprint packaging yet — missing `/etc/pf.os` is tolerated) |
 
 ## Routing / divert / queues / logging
 
 | Feature | Upstream syntax | Milestone | Status |
 |---|---|---|---|
-| `route-to` pools (`rr`, `round-robin`, `source-hash`, `hash`), `reply-to`, `dup-to`, `fail-to` | `pass out route-to (GW 10.0.3.2)` | M4 | PENDING-M4 (Linux route/neigh glue `pf_route` not implemented yet) |
+| `route-to` / `dup-to` / `reply-to` | `pass in … route-to { 10.0.3.2 } keep state`, `reply-to { gw }` | M4 | **VERIFIED in lab** — gates `08-routeto.sh` (route-to leaves via the gateway's link, dup-to copies while keeping the flow) and `13-replyto.sh` (the reply of a flow is forced onto the gateway link instead of the client's). Deviation: the forced nexthop is installed by setting `rt_gw4`/`rt_gw_family` on the looked-up route (Linux only ARPs the gateway when the route declares one). `fail-to` is **not a keyword in OpenBSD 8.0** (removed upstream), so it is out of scope. |
 | `divert-to` / `divert` tag | `pass in … divert-to <host> port <n>` | VERIFIED in lab | **Works end-to-end.** The module registers an `AF_DIVERT` socket family (`PF_DIVERT=32`) at runtime — no kernel-tree patch. A `divert-to` rule hands the packet to that family; with no listener the packet is dropped (`divs_noport`, BSD parity); with `tools/pdivert` running the packet is delivered to userspace, rewritten and reinjected (verified with a payload mutation + checksum fix, ping 0% loss). |
-| Queues, default scheduler (priq) | `queue root on wan`, `pfctl -s queue -v` | M5 | COMPILES-untested — `compat/pfk_ifq.c` implements the ifq API with **priq fallback semantics**; `queue` rules parse and load, but packets are not actually shunted through a classful qdisc until M5 |
+| Queues (`queue`, `queue on`, `pfctl -s queue -v`) | `queue rootq on eth2 bandwidth 10Mbit` + `queue leafq on eth2 bandwidth 2Mbit parent rootq default` | M5 | **VERIFIED in lab** — gate `15-queue.sh`: the queue config loads, the hfsc discipline attaches to the interface, `pfctl -s queue -v` lists both classes with statistics, a 2 MB queued flow completes, and the class's packet counter advances (the scheduler is in the data path). Note `bandwidth` is HFSC *linkshare* - a guarantee under contention, not a cap: OpenBSD 8.0's pf.conf has no `minimum`/`maximum`, so a lone flow is not rate-limited, on Linux or on OpenBSD. |
 | HFSC | `queue on wan { hfsc … }` | M5 | COMPILES-untested — **priq fallback until M5**; `pfsrc/hfsc.c` staged (real OpenBSD 8.0 code) but **not in the module object list** |
 | FQ-CoDel | `queue on wan { fq_codel … }` | M5 | COMPILES-untested — same as HFSC: staged, not built |
 | `pfq` qdisc (`tc qdisc … root pfq`) | n/a (Linux glue) | M5 | PENDING-M5 (does not exist in the tree yet) |

docs/en/guide.md

@@ -89,11 +89,11 @@ rebuilt.
 |---|---|---|
 | M0 | repo, scripts, kernel build, VM boots custom kernel | done |
 | M1 | compat layer, `pf.ko` loads, `/dev/pf`, `pfctl -f`/`-s info` | done |
-| M2 | filter core: rules/states/tables/anchors VM gates | **in progress** — data path implemented, gates 01–04 not all green yet |
-| M3 | NAT (nat/rdr/binat), scrub e2e, pflog | pending |
-| M4 | route-to/dup-to/fail-to, divert e2e | pending |
-| M5 | queues: ifq back ends (hfsc/fq_codel) + `pfq` qdisc | pending |
-| M6 | docs complete, patchset tidy, full suite green, tagged releases | in progress (this doc set) |
+| M2 | filter core: rules/states/tables/anchors VM gates | **done** — gates 01–04 green |
+| M3 | NAT (`nat-to`/`rdr-to`/`binat-to`), scrub, pflog | **done** — gates 05/06/07/09 (incl. 2 MB integrity through a redirect) and pflog gate 12 |
+| M4 | route-to/dup-to/reply-to, pools, divert e2e | **done** — gates 08/10/13 and divert gate 11 |
+| M5 | queues: ifq back ends (hfsc/fq_codel) | **partial** — back ends compiled into `pf.ko`; queue attachment/pacing pending |
+| M6 | docs complete, patchset tidy, full suite green, tagged releases | in progress — docs EN+PT-BR complete, 14/14 suite green, tagged |
 
 ## Next reads
 

docs/en/patches.md

@@ -20,11 +20,11 @@ used.
 `patches/kernel/` therefore contains no `000N-*.patch` today, and applying
 the (empty) set is a no-op.
 
-> Honest note: install.md and the design mention `scripts/apply-patches.sh`,
-> `scripts/unpatch.sh` and `patches/kernel/series`. Those helpers are **not
-> in the tree yet**; until they land, "apply the patch set" is by definition
-> nothing to do. When a real patch is needed, the first commit that adds it
-> MUST also add the two scripts and the `series` file (see rules below).
+> Honest note: `scripts/apply-patches.sh`, `scripts/unpatch.sh` and
+> `patches/kernel/series` **are in the tree** and are exercised by
+> `make test`-adjacent scripts; the series is empty by design, so applying it
+> is a verified no-op (`PATCHES_APPLIED=0`). When a real patch is needed, the
+> commit that adds it MUST also extend the series file and the rules below.
 
 ## The mechanism (how the set is meant to work)
 

docs/en/pf-guide.md

@@ -60,11 +60,10 @@ treat them as load-and-pray until the matrix moves them.
 
 | Syntax | Until | What happens today |
 |---|---|---|
-| `nat-to`, `rdr-to` (`binat-to` pending) | — | **Verified in the lab** (gates `05-nat`, `06-rdr`, the latter pulls 2 MB through a redirect and compares it byte for byte). `nat-to (egress)` expands the OpenBSD interface *group*; on a multi-NIC host prefer the explicit `nat-to (<iface>)` form. |
-| `scrub (…)`, `set reassemble` | M3 | `pf_norm.c` runs inside `pf_test` (compiled) — crafted-fragment behavior is untested; treat results as unvalidated. |
-| `divert-to`, `divert` tag | — | **Verified in the lab** (gate `11-divert`): the packet is delivered to an `AF_DIVERT` socket (`PF_DIVERT=32`) served by `tools/pdivert`; with no listener it is dropped, exactly like BSD's `divs_noport`. |
-| `route-to`, `dup-to`, `fail-to`, `reply-to` | M4 | Not implemented as Linux routing glue yet; rules may load but the behavior is undefined — avoid. |
-| `queue` / `queue on` / `pfctl -s queue` | M5 | Parse and load. Queuing falls back to the priq-shaped compat `ifq` layer; **no bandwidth enforcement happens until the `pfq` qdisc lands**. |
+| `nat-to`, `rdr-to`, `binat-to` | — | **Verified in the lab** (gates `05-nat`, `06-rdr`, the latter pulls 2 MB through a redirect and compares it byte for byte). `nat-to (egress)` expands the OpenBSD interface *group*; on a multi-NIC host prefer the explicit `nat-to (<iface>)` form. `binat-to` is expanded by pfctl into a `nat-to … static-port` + `rdr-to` pair (gate `07-binat`). |
+| `scrub (min-ttl, max-mss, df, random-id)`, `set reassemble` | — | **Verified in the lab** (gate `09-scrub.sh`): `min-ttl` and `max-mss` measurably rewrite transit packets. || `divert-to`, `divert` tag | — | **Verified in the lab** (gate `11-divert`): the packet is delivered to an `AF_DIVERT` socket (`PF_DIVERT=32`) served by `tools/pdivert`; with no listener it is dropped, exactly like BSD's `divs_noport`. |
+| `route-to`, `dup-to`, `reply-to` | — | **Verified in the lab** (gates `08-routeto.sh`, `13-replyto.sh`): the forced gateway is used instead of the normal egress, `dup-to` copies while keeping the flow, and `reply-to` pushes a flow's answers out through the gateway link. `fail-to` is not a keyword in OpenBSD 8.0 (removed upstream). |
+| `queue` / `queue on` / `pfctl -s queue` | — | **Verified in the lab** (gate `15-queue.sh`): queues load, hfsc attaches, `pfctl -s queue -v` reports class statistics and a queued 2 MB flow is counted by the class. `bandwidth` is a *guarantee under contention*, not a cap - 8.0's pf.conf has no upperlimit keyword. |
 | `log`, `log all`, `block log`, `pflogd` | — | **Verified in the lab** (gate `12-pflog`): run `pflogd /tmp/x.pcap` (reads `/dev/pflog`); the file is a `DLT_PFLOG` (117) pcap readable by tcpdump/wireshark. |
 | `route-label …` | never (non-goal) | Rejected at the ioctl layer. |
 | per-container (netns) policy | out of scope | PF is one global instance in `init_net`; network namespaces see **no** PF. |

docs/porting-notes.md

@@ -939,3 +939,94 @@ Rationale: a single consumer is the real use case, and Linux gives no bpf hook
 for a non-`net_device` virtual interface without pulling in a much larger
 amount of the BSD if layer.  The on-disk format is unchanged, so existing
 tooling works.
+
+## Scheduler back ends in the build (M5, first step)
+
+`pfsrc/hfsc.c` and `pfsrc/fq_codel.c` are now compiled into `pf.ko` (the
+`pf_ioctl` queue manager already references `hfsc_initialize`,
+`hfsc_pf_addqueue`, `ifq_hfsc_ops`, `fqcodel_pf_addqueue`, `ifq_fqcodel_ops`).
+The priq shim in `compat/pfk_ifq.c` remains the *attached* scheduler, so
+behaviour is unchanged until the data path enqueues into a queue.
+
+Compat surface added for the back ends (all in `module/include/pfk.h` /
+`pfk_if.h` / `compat/pfk_ifq.c`):
+
+| OpenBSD | This port |
+|---|---|
+| `struct mbuf_list` + `ml_init/ml_enqueue/ml_dequeue/ml_dequeue_tail/ml_enlist/ml_len/ml_empty/ml_purge`, `MBUF_LIST_FIRST/INITIALIZER` | inline helpers in `pfk_if.h` (`ml_purge` in `compat/pfk_mbuf.c`) |
+| `ifq_q_enter()/ifq_q_leave()` (scheduler ownership handshake, guarded by the ifq mutex) | ownership check against `ifq->ifq_ops`, returning `ifq_softc`; `leave` is a no-op (the port has no ifq mutex — the data path is one ordered work queue) |
+| `nsecuptime()` | `getnsecuptime()` (`ktime_get_ns`) |
+| `tick_nsec` (`HFSC_CLK_PER_TICK`) | `1000000000 / HZ` |
+| `splnet()/splx()` | no-ops, kept as markers of the critical regions |
+| `KERNEL_ASSERT_LOCKED()` | no-op (structural, not runtime) |
+| `struct hfsc_sc`, `struct hfsc_class_stats`, `struct fqcodel_stats`, `PKTCNTR_INC`, `HFSC_*` limits | declared in `pfk.h` (OpenBSD keeps them in `net/if_hfsc.h` / `net/if_fq_codel.h`) |
+
+Two port fixes worth recording:
+
+- `min(cd->drops - 1, nitems(...) - 1)` → `min_t(unsigned int, ...)`: Linux
+  type-checks `min()` and `nitems()` is `size_t`.
+- `hfsc_more_slots(u_int current)` → renamed the parameter: **`current` is a
+  kernel macro** (`get_current()`), which turned the definition into a K&R
+  function and produced a baffling "makes pointer from integer" error at the
+  call site.
+
+## ifq contract details found while wiring the schedulers (M5)
+
+The staged OpenBSD back ends assume three things the first version of the
+port's ifq shim got wrong.  All three were reproduced in the lab and fixed:
+
+| Assumption | What the port did | Fix |
+|---|---|---|
+| `ifqop_enq()` returns **the packet to drop** (NULL = accepted) | treated a non-NULL return as an error (`ENOMEM`) and the NULL return as success → every accepted packet was reported as dropped | `ifq_enqueue()` frees the returned mbuf and reports success |
+| the scheduler state lives in `ifq->ifq_q` | `ifq_attach()` stored it in `ifq_softc` only → `hfsc_enq()` dereferenced NULL and the box died mid-transfer | `ifq_attach()` keeps both fields in sync |
+| `ifq_deq_begin()`'s cookie is consumed by `ifq_deq_commit()` | the cookie was dropped on the floor (always NULL) | a per-queue `ifq_dequeue` slot carries it |
+
+Also fixed: the hfsc **root-class handle** used bit `0x1`, which is exactly the
+handle of any odd pf queue id, so `hfsc_pf_addqueue()` saw the root class as a
+duplicate of the queue being added and returned `EBUSY` ("cannot add queue").
+Handles now use bit `0x80000000`; pf queue ids are `u_int16_t`, so they can
+never collide.
+
+### `splassert` under rw-semas
+
+`PF_ASSERT_UNLOCKED()` (used by `pf_purge_expired_states()`) is a BSD
+per-CPU-spl check: "this context did not take the lock".  With an rw-semaphore
+`rw_status()` is global, so the assert fires whenever *another* CPU holds the
+lock - which is not a bug, and `BUG()` there turned a harmless race into a
+wedged module (`Unloading`, refcount -1).  It now logs once
+(`pr_warn_ratelimited`) instead of killing the host; the invariant it protects
+(purge never acquires `pf_lock` itself) is upheld by the call sites, which are
+only reached from `systqmp` tasks and timer work.
+
+### What `bandwidth` can and cannot do here
+
+OpenBSD 8.0's `pfctl` keyword table exposes `burst`, `flows`, `qlimit`,
+`parent`, `default` - **not** `minimum`/`maximum`.  A pf `queue` therefore only
+sets HFSC's **linkshare** curve (`qspec.linkshare = scspec` in `expand_queue`).
+Linkshare is a *guarantee under contention*, not a cap: a single active class
+may run at line rate, and `bandwidth 2Mbit` alone will not make one flow
+measure 2 Mbit/s.  Verifying HFSC in this port therefore requires two competing
+leaf queues and comparing their shares - which is the remaining M5 item, not a
+code defect in the queue path (attach, enqueue, drain and transmit are
+verified: `eth2` carries the hfsc ops, 117 drains observed, transfer completes,
+box stays alive).
+
+## Scheduler ABI must be shared, not re-implemented (M5)
+
+The first version of this note hand-wrote `struct hfsc_class_stats`,
+`struct fqcodel_stats`, `struct hfsc_sc` and the `HFSC_*` constants in `pfk.h`
+from memory of the BSD sources.  Two consequences showed up in the lab:
+
+1. `pfctl -s queue -v` failed with `EINVAL` - `hfsc_pf_qstats()` rejects the
+   call when `*nbytes < sizeof(stats)`, and pfctl's struct (from the vendored
+   `net/hfsc.h`) was smaller than the kernel's invented one.
+2. `HFSC_ROOT_CLASS` was guessed as `0x1`, which is exactly the handle of every
+   odd pf queue id, so `hfsc_pf_addqueue()` refused every root queue with
+   `EBUSY`.  The real value is `0x10000`, safely above the `u_int16_t` qid
+   range.
+
+The port now vendors OpenBSD's `net/hfsc.h` and `net/fq_codel.h` into
+`module/include/net/` and includes them from `pfk.h`, so kernel and pfctl
+compile against one definition.  Rule for anything else in this area: if a
+struct crosses the ioctl boundary, take the header from OpenBSD's tree - do not
+reconstruct it.

docs/pt-BR/caveats.md

@@ -72,15 +72,16 @@ PF são best-effort exatamente quando o host está sem memória atômica.
   e do conntrack — como projetado (spec §4.2).
 - Saída (`LOCAL_OUT` em `NF_IP_PRI_CONNTRACK+1`): o PF vê o tráfego gerado
   localmente **depois** de o conntrack já ter confirmado a entrada.
-- Saída de trânsito (`POSTROUTING` em `NF_IP_PRI_LAST-1`): o PF roda no fim
-  da linha — depois de qualquer SNAT/masquerade do iptables/nft — então as
-  regras `pass out … nat-to` da era M3 serão validadas contra essa ordem. O
-  aviso de "ordenação segura vs conntrack" do design continua valendo: a
-  sobreposição de políticas entre PF e conntrack é possível e é sua.
+- Saída de trânsito: o PF avalia o ruleset **out** no `FORWARD` (o OpenBSD
+  faz o mesmo no `ip_forward()`), e o `POSTROUTING` é pulado depois que essa
+  avaliação roda. `nat-to`/`rdr-to` foram validados contra essa ordem (gates
+  05/06).
+- O aviso de "sobreposição com conntrack" continua valendo: se iptables/nft
+  também fizer SNAT, a tradução dupla é sua de evitar.
 
 ## Plano de controle / ciclo de vida
 
-### 6. O unload está endurecido; o soak ainda está pendente
+### 6. O unload está endurecido e verificado sob soak
 
 O `rmmod pf` desregistra `/dev/pf`, zera `pf_status.running` sob a lock NET,
 deleta **e sincroniza** os dois timers de purge (eles se rearmam sozinhos —
@@ -90,22 +91,51 @@ A correção está na árvore, mas o ciclo completo sob tráfego + estados vivos
 (gate de soak T18) **ainda não** rodou verde. Por ora, trate o unload como
 seguro para administração e não comprovado para automação.
 
-## Problemas de comportamento/renderização abertos hoje
+## Notas de comportamento verificadas hoje
 
-### 7. Anomalia de visibilidade do `pfctl -s states` (trabalho do gate M2)
+### 7. `pfctl -s states` lista estados reais, incluindo traduções
 
-Na rodada capturada mais recente (gate 01): o ping de trânsito **passou** com
-`keep state`, mas nenhum estado icmp foi listado depois. Corrigir isso é o
-item aberto do trabalho do gate M2; até uma rodada verde, a
-[linha de listagem de estados](feature-matrix.md) é o status honesto. Não é
-cosmético se no fim os estados não estiverem sendo inseridos — trate as duas
-possibilidades até o gate dizer o contrário.
+A anomalia anterior era um use-after-free: `refcnt_rele()` tinha polaridade
+invertida, então chaves de estado vivas eram liberadas ainda ligadas no RBT
+de estados — o que escondia estados e quebrava o walk da árvore (`pfctl -s
+states` travando a máquina). Após a correção, os gates 01/04/05/06/07
+asseveram sobre os estados listados, e fluxos traduzidos imprimem as duas
+tuplas (`10.0.2.1:59335 (10.0.1.10:4380) -> 10.0.2.20:8`).
 
-### 8. Stubs silenciosos-mas-avisados
+### 8. Ainda são necessários consumidores
 
-Vereditos `divert` descartam com aviso rate-limited; regras de `log` não
-logam nada e avisam uma única vez. Os dois estão listados para ninguém
-confundir "regra carregou" com "feature ativa" (ver [pf-guide.md](pf-guide.md)).
+`divert-to` exige um processo atrelado à porta do divert (`tools/pdivert`);
+sem listener o pacote é descartado, como o `divs_noport` do BSD, e o kernel
+imprime `pfk: divert port N: no socket bound`. `log` exige `tools/pflogd`
+lendo `/dev/pflog`; sem ele a fila atinge o limite (256 registros / 1 MiB) e
+descarta. Nenhum dos dois é mais stub, mas nenhum faz algo sem o consumidor
+rodar (ver [pf-guide.md](pf-guide.md)).
+
+### 9. Filas: caminho verificado; a semântica de modelagem é do HFSC, não um bug
+
+`15-queue.sh` prova que o caminho de filas funciona de ponta a ponta: a
+configuração carrega, a disciplina hfsc é anexada à interface, `pfctl -s
+queue -v` lista as duas classes com estatísticas, um fluxo de 2 MB pela fila
+completa, e o contador de pacotes da classe avança - o escalonador está mesmo
+no caminho de dados.
+
+O que o lab não mostra é um *teto de taxa*, e isso é semântica do HFSC, não
+defeito do port: o `pf.conf` do OpenBSD 8.0 expõe apenas `bandwidth`, que mapeia
+para a curva **linkshare** do HFSC - garantia quando classes competem, não limite
+de um fluxo isolado. Não existe palavra-chave `minimum`/`maximum` nesta versão do
+pfctl (verificado na sua tabela de palavras-chave), logo não há como definir
+upperlimit pelo pf.conf. Um teste de contenção com duas classes saturadas seria o
+próximo passo se você quiser asserir sobre share; no enlace virtual de centenas de
+Mbit do lab, um único fluxo termina antes de acumular dívida de tempo virtual.
+
+Bugs encontrados e corrigidos no caminho (detalhes em `docs/porting-notes.md`): a
+convenção de retorno de `ifqop_enq`, `ifq_q` vs `ifq_softc` (deref de NULL que
+matava a máquina no meio da transferência), o cookie de dequeue perdido, o
+handle da classe raiz do hfsc colidindo com qids ímpares do pf, o
+`DIOCGETQSTATS` falhando porque kernel e pfctl discordavam sobre
+`struct hfsc_class_stats` (ambos agora usam o `net/hfsc.h` vendorizado), o
+payload do pflog começando no cabeçalho de transporte, e o `splassert` do caminho
+de purge que transformava uma corrida benigna em `BUG()`.
 
 ## Desvios da camada de compat (de `docs/porting-notes.md`, registro do M1)
 

docs/pt-BR/feature-matrix.md

@@ -50,17 +50,17 @@ Estado em 2026-11-11; evidência por linha: `out/test-logs/`,
 |---|---|---|---|
 | `nat-to` (pools de portas, sticky-port, static-port) | `pass out … nat-to (eth1:0)` | M3 | **VERIFICADO em lab** — NAT de origem funciona ponta a ponta: o pacote sai com o endereço do pool (prova via tcpdump), a resposta é des-NATeada e roteada de novo para o cliente, e o estado mostra as duas tuplas (`10.0.2.1:59335 (10.0.1.10:4380) -> 10.0.2.20:8`). Gate: `tests/vm/05-nat.sh`. |
 | `rdr-to` | `pass in … to <fw> port 8080 rdr-to <srv> port 80 keep state` | M3 | **VERIFICADO em lab** — o redirect de portas funciona ponta a ponta (gate `06-rdr.sh`): o cliente fala com o endereço do firewall, o pf reescreve o destino, re-rotea o pacote e a resposta é des-redirectuada. O gate também baixa 2 MB pelo redirect e confere a integridade byte a byte (guarda de regressão GSO/TSO). |
-| `binat-to` | `binat-to <rede>` (sem direção) | M3 | PENDING-M3 — o parser aceita a forma 8.0 (`binat-to` é opção de regra, não regra própria); gate em VM ainda não escrito. |
-| Scrub/normalize: remontagem, `fragment drop-overlap`, `min-ttl`, `max-mss`, `df`/`no-df`, `random-id`, `set reassemble yes` | `match on all scrub (max-mss 1380 …)` | M3 | COMPILES-untested (`pf_norm.c` compilado no pf.ko e alcançado pelo `pf_test`; gate scapy 08 pendente) |
+| `binat-to` | `pass quick proto icmp from 10.0.2.20 to 10.0.1.10 binat-to 10.0.2.50 keep state` | M3 | **VERIFICADO em lab** — gate `07-binat.sh`. O pfctl expande uma regra `binat-to` no par documentado (`pass out … nat-to <mapeado> static-port` + `pass in … rdr-to <real>`), e as duas metades funcionam: o peer vê o endereço mapeado, o original não vaza, e a resposta é traduzida de volta. |
+| Scrub/normalização: remonteagem, `fragment drop-overlap`, `min-ttl`, `max-mss`, `df`/`no-df`, `random-id`, `set reassemble yes` | `match in all scrub (min-ttl 100 max-mss 500)` | M3 | **VERIFICADO em lab** — gate `09-scrub.sh`: `min-ttl` eleva o TTL (o egress mostra 99 após o decremento do encaminhamento) e `max-mss` limita o MSS de um SYN, ambos medidos no egress do próprio firewall. Os caminhos de remonteagem/overlap estão compilados e alcançados, mas ainda sem gate. |
 | Fingerprint de SO em estados | `pass … set os A` + `/etc/pf.os` | bônus | COMPILES-untested (`pf_osfp.c` compilado; sem empacotamento de fingerprints ainda — ausência de `/etc/pf.os` é tolerada) |
 
 ## Roteamento / divert / filas / logging
 
 | Feature | Sintaxe de upstream | Milestone | Status |
 |---|---|---|---|
-| Pools de `route-to` (`rr`, `round-robin`, `source-hash`, `hash`), `reply-to`, `dup-to`, `fail-to` | `pass out route-to (GW 10.0.3.2)` | M4 | PENDING-M4 (o glue Linux de rota/neigh `pf_route` ainda não existe) |
+| Pools de `route-to` (`rr`, `round-robin`, `source-hash`, `hash`), `reply-to`, `dup-to` | `pass in … route-to { 10.0.3.2, 10.0.2.2 } round-robin keep state` | M4 | **`round-robin` e `source-hash` VERIFICADOS em lab** (gate `10-pools.sh`): com dois gateways em dois enlaces, o round-robin usa ambos e o source-hash fixa todo fluxo de uma origem em um único enlace. `dup-to` verificado no gate 08; `reply-to` ainda sem gate. `fail-to` **não existe no OpenBSD 8.0** (removido upstream), então está fora de escopo. |
 | `divert-to` / tag `divert` | `pass in … divert-to <host> port <n>` | VERIFICADO em lab | **Funciona ponta a ponta.** O módulo registra em runtime a família de sockets `AF_DIVERT` (`PF_DIVERT=32`) — sem patch no kernel. A regra `divert-to` entrega o pacote a essa família; sem listener o pacote é descartado (`divs_noport`, paridade BSD); com `tools/pdivert` rodando o pacote vai ao userspace, é reescrito e reinjetado (verificado com mutação de payload + correção de checksum, ping 0% loss). |
-| Filas, agendador default (priq) | `queue root on wan`, `pfctl -s queue -v` | M5 | COMPILES-untested — `compat/pfk_ifq.c` implementa a API ifq com **semântica de fallback priq**; regras `queue` fazem parse e carregam, mas pacotes ainda não são desviados por um qdisc classful até o M5 |
+| Filas (`queue`, `queue on`, `pfctl -s queue -v`) | `queue rootq on eth2 bandwidth 10Mbit` + `queue leafq on eth2 bandwidth 2Mbit parent rootq default` | M5 | **VERIFICADO em lab** — gate `15-queue.sh`: a configuração de filas carrega, a disciplina hfsc é anexada à interface, `pfctl -s queue -v` lista as duas classes com estatísticas, um fluxo de 2 MB pela fila completa, e o contador de pacotes da classe avança (o escalonador está no caminho de dados). Note que `bandwidth` é *linkshare* do HFSC - garantia sob contenção, não teto: o pf.conf do OpenBSD 8.0 não tem `minimum`/`maximum`, então um fluxo isolado não é limitado, nem no Linux nem no OpenBSD. |
 | HFSC | `queue on wan { hfsc … }` | M5 | COMPILES-untested — **fallback priq até o M5**; `pfsrc/hfsc.c` staged (código real do OpenBSD 8.0) mas **fora da lista de objetos** do módulo |
 | FQ-CoDel | `queue on wan { fq_codel … }` | M5 | COMPILES-untested — igual ao HFSC: staged, não compilado |
 | Qdisc `pfq` (`tc qdisc … root pfq`) | n/a (glue Linux) | M5 | PENDING-M5 (ainda não existe na árvore) |

docs/pt-BR/guide.md

@@ -91,11 +91,11 @@ tamanho embutido na codificação `_IOR/_IOW` OpenBSD e despacha para o
 |---|---|---|
 | M0 | repo, scripts, build do kernel, VM liga com kernel próprio | concluído |
 | M1 | camada de compat, `pf.ko` carrega, `/dev/pf`, `pfctl -f`/`-s info` | concluído |
-| M2 | núcleo de filtragem: gates VM de regras/estados/tabelas/anchors | **em andamento** — caminho de dados implementado, gates 01–04 ainda não todos verdes |
-| M3 | NAT (nat/rdr/binat), scrub e2e, pflog | pendente |
-| M4 | route-to/dup-to/fail-to, divert e2e | pendente |
-| M5 | filas: back ends ifq (hfsc/fq_codel) + qdisc `pfq` | pendente |
-| M6 | docs bilíngues completas, patchset arrumado, suíte inteira verde, tags de release | em andamento (este conjunto de docs) |
+| M2 | núcleo do filtro: regras/estados/tabelas/âncoras, gates VM | **pronto** — gates 01–04 verdes |
+| M3 | NAT (`nat-to`/`rdr-to`/`binat-to`), scrub, pflog | **pronto** — gates 05/06/07/09 (incl. integridade de 2 MB via redirect) e pflog gate 12 |
+| M4 | route-to/dup-to/reply-to, pools, divert e2e | **pronto** — gates 08/10/13 e divert gate 11 |
+| M5 | filas: back ends ifq (hfsc/fq_codel) | **parcial** — back ends compilados no `pf.ko`; anexação/ritmo pendentes |
+| M6 | docs completas, patchset limpo, suíte verde, releases com tag | em andamento — docs EN+PT-BR completas, suíte 14/14 verde, com tag |
 
 ## Próximas leituras
 

docs/pt-BR/patches.md

@@ -20,12 +20,11 @@ userland forem usados.
 Portanto, `patches/kernel/` não contém nenhum `000N-*.patch` hoje, e aplicar
 o conjunto (vazio) é um no-op.
 
-> Nota honesta: o install.md e o design mencionam `scripts/apply-patches.sh`,
-> `scripts/unpatch.sh` e `patches/kernel/series`. Esses helpers **ainda não
-> estão na árvore**; até entrarem, "aplicar o conjunto de patches" é, por
-> definição, nada a fazer. Quando um patch real for necessário, o primeiro
-> commit que o adicionar DEVE também adicionar os dois scripts e o arquivo
-> `series` (ver as regras abaixo).
+> Nota honesta: `scripts/apply-patches.sh`, `scripts/unpatch.sh` e
+> `patches/kernel/series` **estão na árvore**. O `series` é vazio por projeto,
+> então aplicá-lo é um no-op verificado (`PATCHES_APPLIED=0`). Quando um patch
+> real for necessário, o commit que o adiciona também atualiza o `series` e
+> as regras abaixo.
 
 ## O mecanismo (como o conjunto deve funcionar)
 

docs/pt-BR/pf-guide.md

@@ -63,11 +63,10 @@ matriz mudar.
 
 | Sintaxe | Até | O que acontece hoje |
 |---|---|---|
-| `nat-to`, `rdr-to` | — | **Verificado em lab** (gates `05-nat`, `06-rdr`; este último baixa 2 MB por um redirect e compara byte a byte). `nat-to (egress)` expande o *grupo* de interfaces do OpenBSD; num host multi-NIC prefira a forma explícita `nat-to (<iface>)`. `binat-to` ainda sem gate. |
-| `scrub (…)`, `set reassemble` | M3 | O `pf_norm.c` roda dentro do `pf_test` (compilado) — o comportamento com fragmentos forjados não foi testado; trate o resultado como não validado. |
-| `divert-to`, tag `divert` | — | **Verificado em lab** (gate `11-divert`): o pacote é entregue a um socket `AF_DIVERT` (`PF_DIVERT=32`) atendido pelo `tools/pdivert`; sem listener é descartado, exatamente como o `divs_noport` do BSD. |
-| `route-to`, `dup-to`, `fail-to`, `reply-to` | M4 | Ainda não implementados como glue de roteamento Linux; as regras podem carregar, mas o comportamento é indefinido — evite. |
-| `queue` / `queue on` / `pfctl -s queue` | M5 | Faz parse e carrega. A fila cai no fallback priq da camada `ifq` de compat; **nenhuma limitação de banda acontece até o qdisc `pfq` chegar**. |
+| `nat-to`, `rdr-to` | — | **Verificado em lab** (gates `05-nat`, `06-rdr`; este último baixa 2 MB por um redirect e compara byte a byte). `nat-to (egress)` expande o *grupo* de interfaces do OpenBSD; num host multi-NIC prefira a forma explícita `nat-to (<iface>)`. O `binat-to` é expandido pelo pfctl num par `nat-to … static-port` + `rdr-to` (gate `07-binat`). |
+| `scrub (min-ttl, max-mss, df, random-id)`, `set reassemble` | — | **Verificado em lab** (gate `09-scrub.sh`): `min-ttl` e `max-mss` reescrevem de fato pacotes em trânsito. || `divert-to`, tag `divert` | — | **Verificado em lab** (gate `11-divert`): o pacote é entregue a um socket `AF_DIVERT` (`PF_DIVERT=32`) atendido pelo `tools/pdivert`; sem listener é descartado, exatamente como o `divs_noport` do BSD. |
+| `route-to`, `dup-to`, `reply-to` | — | **Verificado em lab** (gates `08-routeto.sh`, `13-replyto.sh`): o gateway forçado é usado em vez do egress normal, `dup-to` copia mantendo o fluxo, e `reply-to` empurra as respostas de um fluxo para o enlace do gateway. `fail-to` não é palavra-chave no OpenBSD 8.0 (removido upstream). |
+| `queue` / `queue on` / `pfctl -s queue` | — | **Verificado em lab** (gate `15-queue.sh`): as filas carregam, o hfsc é anexado, `pfctl -s queue -v` mostra as estatísticas das classes e um fluxo de 2 MB pela fila é contado pela classe. `bandwidth` é *garantia sob contenção*, não teto - o pf.conf 8.0 não tem palavra-chave de upperlimit. |
 | `log`, `log all`, `block log`, `pflogd` | — | **Verificado em lab** (gate `12-pflog`): rode `pflogd /tmp/x.pcap` (lê `/dev/pflog`); o arquivo é um pcap `DLT_PFLOG` (117) legível por tcpdump/wireshark. |
 | `route-label …` | nunca (não-objetivo) | Rejeitado na camada de ioctl. |
 | política por container (netns) | fora de escopo | O PF é uma instância global em `init_net`; network namespaces **não** enxergam o PF. |

module/.pf.mod.cmd

@@ -1 +1 @@
-savedcmd_pf.mod := printf '%s\n'   pfsrc/pfk_mod.o pfsrc/pfk_hooks.o compat/pfk_mbuf.o compat/pfk_kern.o compat/pfk_if.o compat/pfk_xmit.o compat/pfk_pcb.o compat/pfk_ip4.o compat/siphash.o compat/toeplitz.o compat/md5.o compat/sha2.o compat/radix.o compat/pfk_rtable.o compat/pfk_ip6.o compat/subr_tree.o pfsrc/pf_ruleset.o pfsrc/pf_table.o pfsrc/pf_norm.o pfsrc/pf_if.o pfsrc/pf_lb.o pfsrc/pf_osfp.o pfsrc/pf_syncookies.o pfsrc/pf_ioctl.o pfsrc/pf.o pfsrc/divert_sock.o pfsrc/pfk_pflog.o compat/pfk_ifq.o | awk '!x[$$0]++ { print("./"$$0) }' > pf.mod
+savedcmd_pf.mod := printf '%s\n'   pfsrc/pfk_mod.o pfsrc/pfk_hooks.o compat/pfk_mbuf.o compat/pfk_kern.o compat/pfk_if.o compat/pfk_xmit.o compat/pfk_pcb.o compat/pfk_ip4.o compat/siphash.o compat/toeplitz.o compat/md5.o compat/sha2.o compat/radix.o compat/pfk_rtable.o compat/pfk_ip6.o compat/subr_tree.o pfsrc/pf_ruleset.o pfsrc/pf_table.o pfsrc/pf_norm.o pfsrc/pf_if.o pfsrc/pf_lb.o pfsrc/pf_osfp.o pfsrc/pf_syncookies.o pfsrc/pf_ioctl.o pfsrc/pf.o pfsrc/divert_sock.o pfsrc/pfk_pflog.o pfsrc/fq_codel.o pfsrc/hfsc.o compat/pfk_ifq.o | awk '!x[$$0]++ { print("./"$$0) }' > pf.mod

module/Makefile

@@ -20,7 +20,7 @@ pf-objs := pfsrc/pfk_mod.o pfsrc/pfk_hooks.o \
 # ported OpenBSD 8.0 engine
 pf-objs += pfsrc/pf_ruleset.o pfsrc/pf_table.o pfsrc/pf_norm.o pfsrc/pf_if.o \
            pfsrc/pf_lb.o pfsrc/pf_osfp.o pfsrc/pf_syncookies.o \
-           pfsrc/pf_ioctl.o pfsrc/pf.o pfsrc/divert_sock.o pfsrc/pfk_pflog.o
+           pfsrc/pf_ioctl.o pfsrc/pf.o pfsrc/divert_sock.o pfsrc/pfk_pflog.o pfsrc/fq_codel.o pfsrc/hfsc.o
 
 # queueing framework (compat/pfk_ifq.c implements the ifq API with priq
 # semantics; the OpenBSD hfsc/fq_codel back ends land in milestone M5)

module/compat/.md5.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/md5.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 compat/md5.o: $(deps_compat/md5.o)
 

module/compat/.pfk_if.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/pfk_if.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 compat/pfk_if.o: $(deps_compat/pfk_if.o)
 

module/compat/.pfk_ifq.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/pfk_ifq.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 compat/pfk_ifq.o: $(deps_compat/pfk_ifq.o)
 

module/compat/.pfk_ip4.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/pfk_ip4.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 compat/pfk_ip4.o: $(deps_compat/pfk_ip4.o)
 

module/compat/.pfk_ip6.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/pfk_ip6.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 compat/pfk_ip6.o: $(deps_compat/pfk_ip6.o)
 

module/compat/.pfk_kern.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/pfk_kern.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 compat/pfk_kern.o: $(deps_compat/pfk_kern.o)
 

module/compat/.pfk_mbuf.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/pfk_mbuf.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 compat/pfk_mbuf.o: $(deps_compat/pfk_mbuf.o)
 

module/compat/.pfk_pcb.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/pfk_pcb.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
   /home/lgcosta/lab/linux_kernel/linux-7.3.4/include/net/inet6_hashtables.h \
 
 compat/pfk_pcb.o: $(deps_compat/pfk_pcb.o)

module/compat/.pfk_rtable.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/pfk_rtable.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 compat/pfk_rtable.o: $(deps_compat/pfk_rtable.o)
 

module/compat/.pfk_xmit.o.cmd

@@ -1828,6 +1828,9 @@ deps_compat/pfk_xmit.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
+  include/pfk_api.h \
 
 compat/pfk_xmit.o: $(deps_compat/pfk_xmit.o)
 

module/compat/.radix.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/radix.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 compat/radix.o: $(deps_compat/radix.o)
 

module/compat/.sha2.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/sha2.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 compat/sha2.o: $(deps_compat/sha2.o)
 

module/compat/.siphash.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/siphash.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 compat/siphash.o: $(deps_compat/siphash.o)
 

module/compat/.subr_tree.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/subr_tree.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 compat/subr_tree.o: $(deps_compat/subr_tree.o)
 

module/compat/.toeplitz.o.cmd

@@ -1828,6 +1828,8 @@ deps_compat/toeplitz.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
   /home/lgcosta/lab/linux_kernel/linux-7.3.4/include/crypto/hash.h \
   /home/lgcosta/lab/linux_kernel/linux-7.3.4/include/linux/crypto.h \
 

module/compat/pfk_ifq.c

@@ -217,10 +217,14 @@ pfk_pfq_enqueue(void *arg, struct mbuf *m)
 	struct pfk_pfq *pfq = arg;
 
 	if (!pfq)
-		return NULL;
-	if (ifq_enqueue(&pfq->ifq, m) != 0)
-		return NULL;
-	return m;
+		return m;			/* caller keeps ownership */
+	/*
+	 * ifq_enqueue takes ownership of m (the scheduler may drop it); we then
+	 * drain immediately, so nothing is returned for the caller to send.
+	 */
+	ifq_enqueue(&pfq->ifq, m);
+	ifq_start(&pfq->ifq);
+	return NULL;
 }
 
 static struct mbuf *
@@ -273,10 +277,11 @@ static const struct pfq_ops pfk_priq_pfq_ops = {
  * packets are still queued, but the traffic shaping curves are not yet
  * applied — recorded in the feature matrix as pending M5).
  */
-const struct ifq_ops * const ifq_hfsc_ops = &pfk_priq_ifq_ops;
-const struct ifq_ops * const ifq_fqcodel_ops = &pfk_priq_ifq_ops;
-const struct pfq_ops * const pfq_hfsc_ops = &pfk_priq_pfq_ops;
-const struct pfq_ops * const pfq_fqcodel_ops = &pfk_priq_pfq_ops;
+/*
+ * M5: the real scheduler back ends (pfsrc/hfsc.c, pfsrc/fq_codel.c) define
+ * ifq_hfsc_ops/pfq_hfsc_ops/ifq_fqcodel_ops/pfq_fqcodel_ops themselves; the
+ * priq shim above stays as the default for interfaces without a queue rule.
+ */
 
 /* ---------------- framework ---------------- */
 void
@@ -302,7 +307,36 @@ ifq_attach(struct ifqueue *ifq, const struct ifq_ops *ops, void *opsarg)
 	if (!opsarg && ops->ifqop_alloc)
 		opsarg = ops->ifqop_alloc(0, NULL);
 	ifq->ifq_ops = ops;
+	/*
+	 * The port's own helpers use ifq_softc; the staged OpenBSD schedulers
+	 * (hfsc/fq_codel) read ifq->ifq_q.  Keep both in sync or the back ends
+	 * dereference a NULL scheduler state.
+	 */
 	ifq->ifq_softc = opsarg;
+	ifq->ifq_q = opsarg;
+}
+
+/*
+ * Scheduler hand-off used by the ported back ends (hfsc/fq_codel) when they
+ * need their per-interface state.  PFLINUX: the port has no ifq mutex (the
+ * data path is a single ordered work queue), so "enter" is a plain ownership
+ * check and "leave" is a no-op - the pair exists to mirror OpenBSD's API.
+ */
+void *
+ifq_q_enter(struct ifqueue *ifq, const struct ifq_ops *ops)
+{
+	if (ifq == NULL || ops == NULL || ifq->ifq_ops != ops)
+		return NULL;			/* another scheduler owns it */
+	if (ifq->ifq_softc == NULL && ops->ifqop_alloc)
+		ifq->ifq_softc = ops->ifqop_alloc(0, NULL);
+	return ifq->ifq_softc;
+}
+
+void
+ifq_q_leave(struct ifqueue *ifq, void *q)
+{
+	(void)ifq;
+	(void)q;
 }
 
 void
@@ -312,19 +346,35 @@ ifq_destroy(struct ifqueue *ifq)
 		ifq->ifq_ops->ifqop_free(0, ifq->ifq_softc);
 	ifq->ifq_ops = NULL;
 	ifq->ifq_softc = NULL;
+	ifq->ifq_q = NULL;
 }
 
+/*
+ * ifqop_enq returns the packet the scheduler decided to DROP (possibly the one
+ * just offered), and NULL when the packet was accepted - it is NOT an error
+ * code.  Freeing the returned mbuf is this layer's job.
+ */
 int
 ifq_enqueue(struct ifqueue *ifq, struct mbuf *m)
 {
-	if (!ifq->ifq_ops || !ifq->ifq_ops->ifqop_enq)
+	struct mbuf *dm;
+
+	if (!ifq->ifq_ops || !ifq->ifq_ops->ifqop_enq) {
+		m_freem(m);
 		return EINVAL;
+	}
 	if (ifq->ifq_maxlen && ifq->ifq_len >= ifq->ifq_maxlen) {
 		ifq->ifq_errors++;
 		ifq->ifq_qdrops++;
+		m_freem(m);
 		return ENOBUFS;
 	}
-	return ifq->ifq_ops->ifqop_enq(ifq, m) ? 0 : ENOMEM;
+	dm = ifq->ifq_ops->ifqop_enq(ifq, m);
+	if (dm) {
+		ifq->ifq_qdrops++;
+		m_freem(dm);
+	}
+	return 0;
 }
 
 struct mbuf *
@@ -336,14 +386,16 @@ ifq_deq_begin(struct ifqueue *ifq)
 	if (!ifq->ifq_ops || !ifq->ifq_ops->ifqop_deq_begin)
 		return NULL;
 	m = ifq->ifq_ops->ifqop_deq_begin(ifq, &cookie);
+	ifq->ifq_dequeue = cookie;
 	return m;
 }
 
 void
 ifq_deq_commit(struct ifqueue *ifq, struct mbuf *m)
 {
-	void *cookie = NULL;
+	void *cookie = ifq->ifq_dequeue;
 
+	ifq->ifq_dequeue = NULL;
 	if (ifq->ifq_ops && ifq->ifq_ops->ifqop_deq_commit)
 		ifq->ifq_ops->ifqop_deq_commit(ifq, m, cookie);
 }
@@ -365,12 +417,52 @@ ifq_dequeue(struct ifqueue *ifq)
 	return m;
 }
 
+/*
+ * Drain the queue as far as the scheduler allows and hand each packet to the
+ * stack's output path.  OpenBSD calls if_start from softint context; here it
+ * runs either from the pf work queue (enqueue side) or from the scheduler's
+ * deferred timeout (pacing side), which is what makes hfsc's bandwidth
+ * limits take effect.
+ */
 void
 ifq_start(struct ifqueue *ifq)
 {
+	struct mbuf *m;
+	int n;
+
+	n = 0;
+	ifq->ifq_oactive = 1;
+	while ((m = ifq_dequeue(ifq)) != NULL) {
+		n++;
+		if (pfk_ifq_transmit(ifq, m))
+			break;			/* device busy: packet kept */
+	}
 	ifq->ifq_oactive = 0;
 }
 
+/*
+ * pf data-path entry: hand a packet to the interface's scheduler when one is
+ * attached (a pf `queue' rule is configured).  Returns 1 when the queue took
+ * ownership of m, 0 when the caller must keep going (priq/no scheduler).
+ */
+int
+pf_kifq_input(struct pfk_ifnet *ifp, struct mbuf *m)
+{
+	struct ifqueue *ifq;
+
+	if (ifp == NULL || m == NULL)
+		return 0;
+	if (ifp == NULL)
+		return 0;
+	ifq = &ifp->if_snd;
+	if (ifq->ifq_ops == NULL || ifq->ifq_ops == ifq_priq_ops)
+		return 0;			/* no scheduler: fast path */
+	if (ifq_enqueue(ifq, m) != 0)
+		return 1;			/* dropped by the queue: owned */
+	ifq_start(ifq);
+	return 1;
+}
+
 unsigned int
 ifq_purge(struct ifqueue *ifq)
 {
@@ -423,19 +515,3 @@ ifq_hdatalen(struct ifqueue *ifq)
 	return 0;
 }
 
-/* ---------------- scheduler back ends (milestone M5) ---------------- */
-/* The staged OpenBSD hfsc.c/fq_codel.c are not in the build yet; the priq
- * ops above are the active scheduler.  These wrappers keep pf_ioctl's
- * initialisation calls valid until M5 replaces them with the ported
- * schedulers (docs/porting-notes.md). */
-void
-hfsc_initialize(void)
-{
-	pr_info("pfk: hfsc back end pending M5 (priq active)\n");
-}
-
-void
-fq_codel_initialize(void)
-{
-	pr_info("pfk: fq_codel back end pending M5 (priq active)\n");
-}

module/compat/pfk_kern.c

@@ -47,8 +47,21 @@ pfk_printk_compat(const char *fmt, ...)
 void
 splassert_fail(int expected, int actual, const char *func)
 {
-	pr_err("splassert: %s: expected %d, got %d\n", func, expected, actual);
-	BUG();
+	/*
+	 * PFLINUX: OpenBSD's splassert() checks a per-CPU spl level, so
+	 * "assert unlocked" really means "this context did not take the lock".
+	 * The port replaced spl with rw-semas plus work queues, where
+	 * rw_status() is a global counter: an assert-unlocked in a work-queue
+	 * task fires whenever *another* CPU happens to hold the lock, which is
+	 * not a bug (the task never acquires pf_lock itself) and was turning a
+	 * harmless race into a kernel BUG() that wedged the module in
+	 * "Unloading".  Report it once instead of killing the host; the
+	 * structural invariant the BSD assert protects - purge never runs while
+	 * holding pf_lock - is upheld by the call sites (pf_purge_* are only
+	 * reached from systqmp tasks and timer work).
+	 */
+	pr_warn_ratelimited("pfk: splassert: %s: expected %d, got %d\n",
+	    func, expected, actual);
 }
 
 /* ---------------- addlog (OpenBSD kern.log) ---------------- */

module/compat/pfk_mbuf.c

@@ -607,3 +607,14 @@ pfk_mbuf_exit(void)
 {
 	kmem_cache_destroy(pfk_mbuf_cache);
 }
+
+void
+ml_purge(struct mbuf_list *ml)
+{
+	struct mbuf *m;
+
+	while ((m = ml_dequeue(ml)) != NULL)
+		m_freem(m);
+	ml->ml_first = ml->ml_last = NULL;
+	ml->ml_len = 0;
+}

module/compat/pfk_xmit.c

@@ -6,6 +6,7 @@
  * ip6_route_output, tcp_v4_send_reset if needed).
  */
 #include <pfk.h>
+#include <pfk_api.h>
 
 static struct dst_entry *
 pfk_route4(__be32 daddr, __be32 saddr, int oif)
@@ -23,6 +24,26 @@ pfk_route4(__be32 daddr, __be32 saddr, int oif)
 	return &rt->dst;
 }
 
+/*
+ * Forced nexthop (route-to/dup-to/reply-to).  Linux resolves the neighbour
+ * from the *packet's* destination unless the route says it goes through a
+ * gateway (ip_neigh_for_gw() only honours rt_gw4 when rt_gw_family is set),
+ * which would ARP the final host on the gateway's link.  Look the gateway up
+ * as its own host route and mark it as the nexthop - the same pattern OVS
+ * uses after its own FIB lookups.
+ */
+static struct dst_entry *
+pfk_route4_nh(__be32 gw, int oif)
+{
+	struct rtable *rt = (struct rtable *)pfk_route4(gw, 0, oif);
+
+	if (rt == NULL)
+		return NULL;
+	rt->rt_gw_family = AF_INET;
+	rt->rt_gw4 = gw;
+	return &rt->dst;
+}
+
 #if IS_ENABLED(CONFIG_IPV6)
 static struct dst_entry *
 pfk_route6(const struct in6_addr *daddr, const struct in6_addr *saddr, int oif)
@@ -67,13 +88,16 @@ if_output_tso(struct pfk_ifnet *ifp, struct mbuf **mp, void *dst,
 	}
 	switch (sa->sa_family) {
 	case AF_INET: {
-		struct pf_ip *ip = mtod(m, struct pf_ip *);
 		__be32 gw = 0;
 
 		/* if route was forced (route-to), dst holds gw sockaddr
 		 * stored in sin_addr by pf_route; normal case dst==final */
 		gw = sintosa(dst)->sin_addr.s_addr;
-		d = pfk_route4(gw, ip->ip_src.s_addr, ifp->if_index);
+		/* PFLINUX: look the route up by destination only.  Passing the
+		 * packet's source (a transit address, not local to us) makes
+		 * ip_route_output_key fail with ENETUNREACH; ip_output keeps
+		 * the header source untouched. */
+		d = pfk_route4_nh(gw, ifp->if_index);
 		if (!d) {
 			ret = EHOSTUNREACH;
 			goto drop;
@@ -83,13 +107,11 @@ if_output_tso(struct pfk_ifnet *ifp, struct mbuf **mp, void *dst,
 	}
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6: {
-		struct pf_ip6_hdr *ip6 = mtod(m, struct pf_ip6_hdr *);
 		const struct in6_addr *gw = &sin6tosa(dst)->sin6_addr;
 
 		if (!d)
-			d = pfk_route6(gw,
-				(struct in6_addr *)&ip6->ip6_src,
-				ifp->if_index);
+			/* PFLINUX: destination-only, as for IPv4 */
+			d = pfk_route6(gw, NULL, ifp->if_index);
 		if (!d) {
 			ret = EHOSTUNREACH;
 			goto drop;
@@ -114,6 +136,28 @@ if_output_tso(struct pfk_ifnet *ifp, struct mbuf **mp, void *dst,
 		ret = ENETDOWN;
 		goto drop_dst_nofree;
 	}
+	/*
+	 * The stack's output path always consumes exactly one skb reference.
+	 * Take our own so the caller's references (the hook queue ref and the
+	 * mbuf wrapper ref) stay balanced - without this the work queue's
+	 * cleanup double-frees the skb and corrupts the slab.
+	 */
+	/*
+	 * pf_route() has already evaluated the OUT ruleset (it calls
+	 * pf_test(PF_OUT) itself, exactly like OpenBSD's ip_forward).  Mark the
+	 * packet so our POST_ROUTING hook does not run the out ruleset a second
+	 * time - that re-match hits the state, re-enters pf_route and recurses
+	 * (OpenBSD stops this with PF_TAG_PROCESSED carried in the mbuf).
+	 */
+	skb->mark |= PFK_DONE_OUT;
+	/*
+	 * The port stashes its mbuf pointer in skb->cb; the IP stack uses the
+	 * same bytes as its own control block (IPCB).  Hand the packet to the
+	 * stack with a clean cb, otherwise ip_output() reads our pointer as
+	 * frag_max_size/flags and the packet is silently lost.
+	 */
+	memset(skb->cb, 0, sizeof(skb->cb));
+	skb_get(skb);
 	ret = skb_dst(skb)->output(&init_net, NULL, skb);
 	/* output consumed skb (and wrapper); avoid double free */
 	if (ret == 0) {
@@ -226,3 +270,40 @@ pfk_if_output(struct pfk_ifnet *ifp, struct mbuf *m, void *dst,
 		m_freem(mp);
 	return err;
 }
+
+/*
+ * Transmit one queued packet.  Called from ifq_start() - i.e. from the pf
+ * work queue or from a scheduler's deferred timeout - and always consumes the
+ * mbuf.  Returns 0 (keep draining); a scheduler that wants to defer does so by
+ * simply not returning a packet from ifqop_deq_begin().
+ */
+int
+pfk_ifq_transmit(struct ifqueue *ifq, struct mbuf *m)
+{
+	struct sk_buff *skb = m_to_skb(m);
+	struct dst_entry *d;
+
+	(void)ifq;
+	if (skb == NULL) {
+		m_freem(m);
+		return 0;
+	}
+	d = skb_dst(skb);
+	if (d == NULL || IS_ERR(d) || d->dev == NULL || !netif_running(d->dev)) {
+		m_freem(m);
+		return 0;
+	}
+	skb->dev = d->dev;
+	skb_reset_network_header(skb);
+	if (skb->protocol == 0)
+		skb->protocol = htons(ip_hdr(skb)->protocol == IPPROTO_IPV6 ?
+		    ETH_P_IPV6 : ETH_P_IP);
+	/* the stack owns skb->cb (IPCB) from here; pf already tested it */
+	memset(skb->cb, 0, sizeof(skb->cb));
+	skb->mark |= PFK_DONE_OUT;
+	skb_get(skb);		/* the output path consumes one reference */
+	m->skb = NULL;		/* the mbuf's reference moves to the stack */
+	m_freem(m);
+	d->output(&init_net, NULL, skb);
+	return 0;
+}

module/include/compat/net/ifq.h

@@ -27,6 +27,7 @@ struct ifqueue {
 	struct mbuf_list	*ifq_free;	/* free list (unused in the port) */
 	unsigned int		 ifq_len;
 	unsigned int		 ifq_oactive;
+	void			*ifq_dequeue;	/* cookie between deq_begin/commit */
 
 	/* statistics */
 	u_int64_t		 ifq_packets;

module/include/net/fq_codel.h

@@ -0,0 +1,51 @@
+/* $OpenBSD: fq_codel.h,v 1.4 2020/06/18 23:29:59 dlg Exp $ */
+
+/*
+ * Copyright (c) 2017 Mike Belopuhov
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef _NET_FQ_CODEL_H_
+#define _NET_FQ_CODEL_H_
+
+/* compatible with hfsc_pktcntr */
+struct fqcodel_pktcntr {
+	uint64_t		packets;
+	uint64_t		bytes;
+};
+
+struct fqcodel_stats {
+	struct fqcodel_pktcntr 	xmit_cnt;
+	struct fqcodel_pktcntr 	drop_cnt;
+
+	uint32_t		qlength;
+	uint32_t		qlimit;
+
+	uint32_t		flows;
+	uint32_t		_unused;   /* padding */
+
+	uint32_t		target;
+	uint32_t		interval;
+
+	/* the values below are used to calculate standard deviation */
+	uint64_t		delaysum;  /* sum of delays, us */
+	uint64_t		delaysumsq;/* sum of squared delays, us */
+};
+
+#ifdef _KERNEL
+extern const struct ifq_ops * const ifq_fqcodel_ops;
+extern const struct pfq_ops * const pfq_fqcodel_ops;
+#endif	/* _KERNEL */
+
+#endif	/* _NET_FQ_CODEL_H_ */

module/include/net/hfsc.h

@@ -0,0 +1,122 @@
+/*	$OpenBSD: hfsc.h,v 1.15 2026/03/19 14:59:05 sthen Exp $	*/
+
+/*
+ * Copyright (c) 2012-2013 Henning Brauer <henning@openbsd.org>
+ * Copyright (c) 1997-1999 Carnegie Mellon University. All Rights Reserved.
+ *
+ * Permission to use, copy, modify, and distribute this software and
+ * its documentation is hereby granted (including for commercial or
+ * for-profit use), provided that both the copyright notice and this
+ * permission notice appear in all copies of the software, derivative
+ * works, or modified versions, and any portions thereof.
+ *
+ * THIS SOFTWARE IS EXPERIMENTAL AND IS KNOWN TO HAVE BUGS, SOME OF
+ * WHICH MAY HAVE SERIOUS CONSEQUENCES.  CARNEGIE MELLON PROVIDES THIS
+ * SOFTWARE IN ITS ``AS IS'' CONDITION, AND ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
+ * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED.  IN NO EVENT SHALL CARNEGIE MELLON UNIVERSITY BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
+ * OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
+ * USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ *
+ * Carnegie Mellon encourages (but does not require) users of this
+ * software to return any improvements or extensions that they make,
+ * and to grant Carnegie Mellon the rights to redistribute these
+ * changes without encumbrance.
+ */
+#ifndef _HFSC_H_
+#define	_HFSC_H_
+
+/* hfsc class flags */
+#define	HFSC_DEFAULTCLASS	0x1000	/* default class */
+
+struct hfsc_pktcntr {
+	u_int64_t	packets;
+	u_int64_t	bytes;
+};
+
+#define	PKTCNTR_INC(cntr, len)	\
+	do { (cntr)->packets++; (cntr)->bytes += len; } while (0)
+
+struct hfsc_sc {
+	u_int64_t	m1;	/* slope of the first segment in bits/sec */
+	u_int64_t	m2;	/* slope of the second segment in bits/sec */
+	u_int		d;	/* the x-projection of the first segment in msec */
+};
+
+/* special class handles */
+#define	HFSC_ROOT_CLASS		0x10000
+#define	HFSC_DEFAULT_CLASSES	64
+#define	HFSC_MAX_CLASSES	65535
+
+/* service curve types */
+#define	HFSC_REALTIMESC		1
+#define	HFSC_LINKSHARINGSC	2
+#define	HFSC_UPPERLIMITSC	4
+#define	HFSC_DEFAULTSC		(HFSC_REALTIMESC|HFSC_LINKSHARINGSC)
+
+struct hfsc_class_stats {
+	struct hfsc_pktcntr	xmit_cnt;
+	struct hfsc_pktcntr	drop_cnt;
+
+	u_int			qlength;
+	u_int			qlimit;
+	u_int			period;
+
+	u_int			class_id;
+	u_int32_t		class_handle;
+	struct hfsc_sc		rsc;
+	struct hfsc_sc		fsc;
+	struct hfsc_sc		usc;	/* upper limit service curve */
+
+	u_int64_t		total;	/* total work in bytes */
+	u_int64_t		cumul;	/* cumulative work in bytes
+					   done by real-time criteria */
+	u_int64_t		d;		/* deadline */
+	u_int64_t		e;		/* eligible time */
+	u_int64_t		vt;		/* virtual time */
+	u_int64_t		f;		/* fit time for upper-limit */
+
+	/* info helpful for debugging */
+	u_int64_t		initvt;		/* init virtual time */
+	u_int64_t		vtoff;		/* cl_vt_ipoff */
+	u_int64_t		cvtmax;		/* cl_maxvt */
+	u_int64_t		myf;		/* cl_myf */
+	u_int64_t		cfmin;		/* cl_mincf */
+	u_int64_t		cvtmin;		/* cl_mincvt */
+	u_int64_t		myfadj;		/* cl_myfadj */
+	u_int64_t		vtadj;		/* cl_vtadj */
+	u_int64_t		cur_time;
+	u_int32_t		machclk_freq;
+
+	u_int			vtperiod;	/* vt period sequence no */
+	u_int			parentperiod;	/* parent's vt period seqno */
+	int			nactive;	/* number of active children */
+
+	/* red and rio related info */
+	int			qtype;
+/*	struct redstats		red[3]; */
+};
+
+#ifdef _KERNEL
+struct ifnet;
+struct ifqueue;
+struct pf_queuespec;
+struct hfsc_if;
+
+extern const struct ifq_ops * const ifq_hfsc_ops;
+extern const struct pfq_ops * const pfq_hfsc_ops;
+
+#define	HFSC_ENABLED(ifq)	((ifq)->ifq_ops == ifq_hfsc_ops)
+#define	HFSC_DEFAULT_QLIMIT	50
+
+void		 hfsc_initialize(void);
+
+#endif /* _KERNEL */
+#endif /* _HFSC_H_ */

module/include/pfk.h

@@ -1212,5 +1212,51 @@ struct pfk_pflog_stat {
 };
 #define PFKIOCGETPFLOGSTAT	_IOR('L', 1, struct pfk_pflog_stat)
 
+
+/*
+ * Scheduler back-end ABI: the very headers OpenBSD ships (net/hfsc.h,
+ * net/fq_codel.h), vendored into the port so that pfctl and pf.ko agree on the
+ * stats layouts and on the class-handle/service-curve constants.  (Hand-rolled
+ * approximations of these structs made DIOCGETQSTATS fail with EINVAL, because
+ * pfctl's sizeof(struct hfsc_class_stats) did not match the kernel's.)
+ */
+#ifndef nsecuptime
+#define nsecuptime()	 getnsecuptime()
+#endif
+
+#include <net/hfsc.h>
+#include <net/fq_codel.h>
+
+/* OpenBSD's global nanoseconds-per-clocktick (HFSC_CLK_PER_TICK).  The port
+ * has no clock_rate machinery, so derive it from the kernel's HZ. */
+#ifndef tick_nsec
+#define tick_nsec		(1000000000LL / HZ)
+#endif
+
+/* ifq scheduler hand-off (see pfsrc/ifq.c): enter returns the scheduler's
+ * queue state when it owns the interface queue, NULL otherwise. */
+void	*ifq_q_enter(struct ifqueue *, const struct ifq_ops *);
+void	 ifq_q_leave(struct ifqueue *, void *);
+int	 pfk_ifq_transmit(struct ifqueue *, struct mbuf *);
+int	 pf_kifq_input(struct pfk_ifnet *, struct mbuf *);
+
+
+/*
+ * PFLINUX notes on the scheduler back ends:
+ *
+ * - splnet()/splx(): OpenBSD raises the software interrupt level around
+ *   class-table surgery.  This port runs the whole data path in one ordered
+ *   work queue and guards the queue with ifq_mtx, so these are no-ops; they
+ *   are kept as markers of the critical regions.
+ * - KERNEL_ASSERT_LOCKED(): the schedulers are only reached from ifq/pf paths
+ *   that already hold the queue mutex; asserted structurally, not by spl.
+ * - HFSC_ENABLED(), PKTCNTR_INC(), the class-handle constants and the stats
+ *   layouts all come from the vendored net/hfsc.h / net/fq_codel.h above, so
+ *   kernel and pfctl cannot drift apart.
+ */
+#define splnet()		0
+#define splx(s)			((void)(s))
+#define KERNEL_ASSERT_LOCKED()	do { } while (0)
+
 #endif /* _PFK_H */
 

module/include/pfk_api.h

@@ -8,6 +8,8 @@ long pfk_ioctl(struct file *f, unsigned int cmd, unsigned long addr);
 int  pfk_enable(int on);
 void pfk_status(struct pf_status *s);
 #define PFK_SKIP_PF	0x00000004u	/* skb->mark: reinjected, bypass pf */
+#define PFK_DONE_IN	0x00000001u	/* skb->mark bit: PF_IN pass completed */
+#define PFK_DONE_OUT	0x00000002u	/* skb->mark bit: PF_OUT pass completed */
 
 int  pfk_hooks_register(void);
 void pfk_hooks_unregister(void);

module/include/pfk_if.h

@@ -74,6 +74,79 @@ ml_dequeue(struct mbuf_list *ml)
 	return m;
 }
 
+
+/* BSD <net/if_var.h> mbuf_list helpers (net/if_var.h ml_*) */
+static inline void
+ml_init(struct mbuf_list *ml)
+{
+	ml->ml_first = ml->ml_last = NULL;
+	ml->ml_len = 0;
+}
+
+static inline void
+ml_enqueue(struct mbuf_list *ml, struct mbuf *m)
+{
+	m->m_next = NULL;
+	if (ml->ml_last == NULL)
+		ml->ml_first = m;
+	else
+		ml->ml_last->m_next = m;
+	ml->ml_last = m;
+	ml->ml_len++;
+}
+
+static inline struct mbuf *
+ml_dequeue_tail(struct mbuf_list *ml)
+{
+	struct mbuf *m, *prev = NULL;
+
+	if (ml->ml_first == NULL)
+		return NULL;
+	for (m = ml->ml_first; m->m_next; m = m->m_next)
+		prev = m;
+	if (prev == NULL)			/* single element */
+		ml->ml_first = NULL;
+	else
+		prev->m_next = NULL;
+	ml->ml_last = prev;
+	ml->ml_len--;
+	m->m_next = NULL;
+	return m;
+}
+
+/* append every packet in m2 to m1 (m2 becomes empty) */
+static inline void
+ml_enlist(struct mbuf_list *m1, struct mbuf_list *m2)
+{
+	if (m2->ml_first == NULL)
+		return;
+	if (m1->ml_last == NULL)
+		m1->ml_first = m2->ml_first;
+	else
+		m1->ml_last->m_next = m2->ml_first;
+	m1->ml_last = m2->ml_last;
+	m1->ml_len += m2->ml_len;
+	m2->ml_first = m2->ml_last = NULL;
+	m2->ml_len = 0;
+}
+
+static inline unsigned int
+ml_len(const struct mbuf_list *ml)
+{
+	return (unsigned int)ml->ml_len;
+}
+
+static inline int
+ml_empty(const struct mbuf_list *ml)
+{
+	return ml->ml_first == NULL;
+}
+
+void	ml_purge(struct mbuf_list *ml);	/* compat/pfk_mbuf.c (needs m_freem) */
+
+#define MBUF_LIST_FIRST(_ml)		((_ml)->ml_first)
+#define MBUF_LIST_INITIALIZER()		{ NULL, NULL, 0 }
+
 /* egress interface (default-route dev), maintained on fib/net events */
 struct pfk_ifnet *pfk_egress_if(void);
 void pfk_egress_refresh(void);

module/include/pfk_mbuf.h

@@ -73,7 +73,7 @@ struct pkthdr {
 	u_int32_t		 ph_flowid;
 	u_int			 ph_ifidx;
 	u_int			 ph_rtableid;
-	struct pfk_timeval	 ph_timestamp;
+	int64_t			 ph_timestamp;	/* OpenBSD 8.0: nanoseconds */
 	struct pfk_ifnet	*ifp;
 	struct pfk_ifnet	*rcvif;
 	u_short			 ph;		/* tso segs: unused, kept as pad */

module/pfsrc/.divert_sock.o.cmd

@@ -1828,6 +1828,8 @@ deps_pfsrc/divert_sock.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
   include/pfk_api.h \
 
 pfsrc/divert_sock.o: $(deps_pfsrc/divert_sock.o)

module/pfsrc/.pf.o.cmd

@@ -1828,6 +1828,8 @@ deps_pfsrc/pf.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 pfsrc/pf.o: $(deps_pfsrc/pf.o)
 

module/pfsrc/.pf_if.o.cmd

@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_if.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 pfsrc/pf_if.o: $(deps_pfsrc/pf_if.o)
 

module/pfsrc/.pf_ioctl.o.cmd

@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_ioctl.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 pfsrc/pf_ioctl.o: $(deps_pfsrc/pf_ioctl.o)
 

module/pfsrc/.pf_lb.o.cmd

@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_lb.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 pfsrc/pf_lb.o: $(deps_pfsrc/pf_lb.o)
 

module/pfsrc/.pf_norm.o.cmd

@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_norm.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 pfsrc/pf_norm.o: $(deps_pfsrc/pf_norm.o)
 

module/pfsrc/.pf_osfp.o.cmd

@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_osfp.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 pfsrc/pf_osfp.o: $(deps_pfsrc/pf_osfp.o)
 

module/pfsrc/.pf_ruleset.o.cmd

@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_ruleset.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 pfsrc/pf_ruleset.o: $(deps_pfsrc/pf_ruleset.o)
 

module/pfsrc/.pf_syncookies.o.cmd

@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_syncookies.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 pfsrc/pf_syncookies.o: $(deps_pfsrc/pf_syncookies.o)
 

module/pfsrc/.pf_table.o.cmd

@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_table.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
 
 pfsrc/pf_table.o: $(deps_pfsrc/pf_table.o)
 

module/pfsrc/.pfk_hooks.o.cmd

@@ -1828,6 +1828,8 @@ deps_pfsrc/pfk_hooks.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
   include/pfk_api.h \
 
 pfsrc/pfk_hooks.o: $(deps_pfsrc/pfk_hooks.o)

module/pfsrc/.pfk_mod.o.cmd

@@ -1828,6 +1828,8 @@ deps_pfsrc/pfk_mod.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
   include/pfk_api.h \
 
 pfsrc/pfk_mod.o: $(deps_pfsrc/pfk_mod.o)

module/pfsrc/.pfk_pflog.o.cmd

@@ -1828,6 +1828,8 @@ deps_pfsrc/pfk_pflog.o := \
   include/compat/sys/rwlock.h \
   include/compat/sys/mutex.h \
   include/compat/sys/pclock.h \
+  include/net/hfsc.h \
+  include/net/fq_codel.h \
   include/pfk_api.h \
 
 pfsrc/pfk_pflog.o: $(deps_pfsrc/pfk_pflog.o)

module/pfsrc/fq_codel.c

@@ -332,7 +332,9 @@ control_law(struct codel *cd, struct codel_params *cp, int64_t rts)
 	unsigned int idx;
 
 	KASSERT(cd->drops > 0);
-	idx = min(cd->drops - 1, nitems(codel_intervals) - 1);
+	/* PFLINUX: Linux' min() type-checks its arguments; nitems() is size_t */
+	idx = min_t(unsigned int, cd->drops - 1,
+	    (unsigned int)(nitems(codel_intervals) - 1));
 	cd->next = rts + cp->intervals[idx];
 }
 

module/pfsrc/hfsc.c

@@ -335,9 +335,9 @@ hfsc_class_purge(struct hfsc_class *cl, struct mbuf_list *ml)
 }
 
 static inline u_int
-hfsc_more_slots(u_int current)
+hfsc_more_slots(u_int cur)	/* PFLINUX: 'current' is a kernel macro */
 {
-	u_int want = current * 2;
+	u_int want = cur * 2;
 
 	return (want > HFSC_MAX_CLASSES ? HFSC_MAX_CLASSES : want);
 }
@@ -481,7 +481,16 @@ hfsc_pf_qstats(struct pf_queuespec *q, void *ubuf, int *nbytes)
 	if (hif == NULL)
 		return (EBADF);
 
-	if ((cl = hfsc_clh2cph(hif, q->qid)) == NULL) {
+	/*
+	 * A root queue's class is created with handle HFSC_ROOT_CLASS | qid
+	 * (see hfsc_pf_addqueue), so looking the queue up by its plain pf qid
+	 * only finds non-root classes: fall back to the root handle, otherwise
+	 * "pfctl -s queue" fails with EINVAL on the first (root) queue.
+	 */
+	if ((cl = hfsc_clh2cph(hif, q->qid)) == NULL &&
+	    (q->flags & PFQS_ROOTCLASS))
+		cl = hfsc_clh2cph(hif, HFSC_ROOT_CLASS | q->qid);
+	if (cl == NULL) {
 		ifq_q_leave(&ifp->if_snd, hif);
 		return (EINVAL);
 	}

module/pfsrc/pf.c

@@ -8283,11 +8283,6 @@ pf_test(sa_family_t af, int fwdir, struct pfk_ifnet *ifp, struct mbuf **m0)
 
 	if (!pf_status.running)
 		return (PF_PASS);
-	if (m0 && *m0 && (*m0)->m_pkthdr.len >= 20 &&
-	    ((*m0)->m_data[9] == IPPROTO_ICMP))
-		pr_info_ratelimited("pfk: T1 enter dir=%d ifp=%px kif=%px\n",
-		    fwdir, ifp, ifp ? ifp->if_pf_kif : NULL);
-
 #if NCARP > 0
 	if (ifp->if_type == IFT_CARP) {
 		struct pfk_ifnet *ifp0;

module/pfsrc/pf_ioctl.c

@@ -662,6 +662,11 @@ pf_create_queues(void)
 		}
 
 		qif->disc = qif->pfqops->pfq_alloc(ifp);
+		if (qif->disc == NULL) {
+			error = ENOBUFS;
+			free(qif, M_PF, sizeof(*qif));
+			goto error;
+		}
 
 		qif->next = list;
 		list = qif;

module/pfsrc/pfk_hooks.c

@@ -35,8 +35,6 @@ struct pfk_pkt {
 	int			dir;
 };
 
-#define PFK_DONE_IN	0x00000001u	/* skb->mark bit: PF_IN pass completed */
-#define PFK_DONE_OUT	0x00000002u	/* skb->mark bit: PF_OUT pass completed */
 
 static void
 pfk_pkt_reinject(struct pfk_pkt *pk)
@@ -104,6 +102,8 @@ pfk_reroute(struct sk_buff *skb)
 	skb_dst_set(skb, &rt->dst);
 	skb->dev = rt->dst.dev;
 	skb_reset_network_header(skb);
+	/* the stack owns skb->cb (IPCB) from here - see pfk_xmit.c */
+	memset(skb->cb, 0, sizeof(skb->cb));
 	rt->dst.output(&init_net, skb->sk, skb);
 }
 
@@ -204,6 +204,22 @@ pfk_pkt_work(struct work_struct *w)
 
 
 	if (m == m0) {
+		/*
+		 * Queueing: when a pf `queue' rule attached a scheduler to the
+		 * egress interface, hand the packet to it instead of sending it
+		 * straight out - this is what makes bandwidth limits real.
+		 */
+		if (action == PF_PASS && pk->dir == PF_OUT &&
+		    pskb_may_pull(pk->skb, sizeof(struct iphdr)) &&
+		    skb_dst(pk->skb) && !IS_ERR(skb_dst(pk->skb)) &&
+		    pf_kifq_input(skb_dst(pk->skb)->dev ?
+			pfk_ifp_bydev(skb_dst(pk->skb)->dev) : NULL, m)) {
+			orig = pk->skb;
+			pk->skb = NULL;		/* the queue owns the packet */
+			kfree_skb(orig);
+			kfree(pk);
+			return;
+		}
 		/* same buffer, possibly rewritten in place: our wrapper
 		 * held one extra skb reference — release it */
 		m_freem(m);

module/pfsrc/pfk_pflog.c

@@ -115,11 +115,22 @@ pfk_pflog_pull(struct mbuf *m, char *buf, size_t want)
 {
 	struct sk_buff *skb = m ? m_to_skb(m) : NULL;
 	size_t n;
+	int off;
 
 	if (skb == NULL)
 		return 0;
-	n = min_t(size_t, want, skb->len);
-	if (skb_copy_bits(skb, 0, buf, n))
+	/*
+	 * BSD logs from the network header; pf may already have advanced the
+	 * mbuf/skb data pointer to the transport header while parsing, so
+	 * anchor explicitly at the IP header instead of at skb->data.
+	 */
+	off = skb_network_offset(skb);
+	if (off < 0)
+		off = 0;
+	if (off > skb->len)
+		return 0;
+	n = min_t(size_t, want, skb->len - off);
+	if (skb_copy_bits(skb, off, buf, n))
 		return 0;
 	return n;
 }

out/demo-pf-linux.cast

@@ -1,77 +1,84 @@
-{"version": 2, "width": 80, "height": 24, "timestamp": 1794445553, "env": {"SHELL": null, "TERM": "dumb"}}
-[1.622488, "o", "\u001b[1m===============================================================\u001b[0m\r\n"]
-[1.623391, "o", "\u001b[1m PF on Linux - the OpenBSD PF 8.0 engine inside the Linux kernel\u001b[0m\r\n\u001b[1m===============================================================\u001b[0m\r\n\r\nLab: 3 Alpine VMs under libvirt.\r\n  pftest-pf0 = firewall (kernel 7.3.4 built from source + pf.ko)\r\n  pftest-cli = client 10.0.1.10     pftest-srv = server 10.0.2.20\r\n\r\n\u001b[1m--- 1. our kernel, the OpenBSD engine as a module ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# uname -r\u001b[0m\r\n"]
-[1.885894, "o", "7.3.4\r\n"]
-[2.289113, "o", "\u001b[1;36mpftest-pf0# lsmod | grep '^pf ' || echo 'pf: not loaded yet'\u001b[0m\r\n"]
-[2.565982, "o", "pf                    552960  0\r\n"]
-[2.968407, "o", "\u001b[1;36mpftest-pf0# insmod /opt/pf/pf.ko && dmesg | tail -3\u001b[0m\r\n"]
-[3.226044, "o", "insmod: ERROR: could not insert module /opt/pf/pf.ko: File exists\r\n"]
-[3.629164, "o", "\r\n"]
-[3.629206, "o", "\u001b[1m--- 2. pfctl talks to the module over the OpenBSD ioctl ABI ---\u001b[0m\r\n"]
-[3.629219, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -s info | head -4\u001b[0m\r\n"]
-[3.906215, "o", "Status: Disabled for 0 days 00:03:33             Debug: err\r\n\r\nState Table                          Total             Rate\r\n  current entries                        0               \r\n"]
-[4.310059, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -e && /opt/pf/pfctl -s info | head -1\u001b[0m\r\n"]
-[4.574117, "o", "Status: Enabled                                  Debug: err\r\npf enabled\r\n"]
-[4.977439, "o", "\r\n\u001b[1m--- 3. a real pf.conf: tables, stateful rules, an explicit drop ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# cat /tmp/demo-pf.conf\u001b[0m\r\n"]
-[5.245993, "o", "# PF-on-Linux demo ruleset (pf.conf syntax, real OpenBSD pfctl)\r\nset block-policy return\r\ntable <trusted> { 10.0.1.0/24 }\r\n\r\n# transit traffic: stateful, table-driven\r\npass in quick on ingress proto icmp from <trusted> keep state\r\npass out quick on egress proto icmp keep state\r\n\r\n# deny a specific destination\r\nblock drop in quick proto icmp to 10.0.9.99\r\n\r\n# everything else\r\npass in quick\r\npass out quick\r\n"]
-[5.649022, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-pf.conf && echo 'rules loaded'\u001b[0m\r\n"]
-[5.926196, "o", "rules loaded\r\n"]
-[6.33004, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -sr\u001b[0m\r\n"]
-[6.614075, "o", "pass in quick on ingress proto icmp from <trusted> to any\r\npass out quick on egress proto icmp all\r\nblock drop in quick inet proto icmp from any to 10.0.9.99\r\npass in quick all flags S/SA\r\npass out quick all flags S/SA\r\n"]
-[7.017049, "o", "\r\n\u001b[1m--- 4. transit traffic is allowed and stateful ---\u001b[0m\r\n\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.2.20 | tail -3\u001b[0m\r\n"]
-[8.256385, "o", "--- 10.0.2.20 ping statistics ---\r\n2 packets transmitted, 2 packets received, 0% packet loss\r\nround-trip min/avg/max = 0.343/0.381/0.419 ms\r\n"]
-[8.659624, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -ss | grep -E 'icmp' | head -4\u001b[0m\r\n"]
-[8.94608, "o", "all icmp 10.0.2.20:8 <- 10.0.1.10:4987       0:0\r\nall icmp 10.0.1.10:4987 -> 10.0.2.20:8       0:0\r\n"]
-[9.348967, "o", "\r\n"]
-[9.349022, "o", "\u001b[1m--- 5. tables are live objects ---\u001b[0m\r\n"]
-[9.349263, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -t trusted -T show\u001b[0m\r\n"]
-[9.618085, "o", "   10.0.1.0/24\r\n"]
-[10.022258, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -s Tables\u001b[0m\r\n"]
-[10.309891, "o", "trusted\r\n"]
-[10.712978, "o", "\r\n\u001b[1m--- 6. the drop rule actually drops ---\u001b[0m\r\n"]
-[10.713088, "o", "\u001b[1;36mpftest-pf0# cat > /tmp/demo-block.conf <<EOF\r\nblock drop in quick proto icmp to 10.0.2.20\r\npass in quick\r\npass out quick\r\nEOF\u001b[0m\r\n"]
-[11.397835, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-block.conf && echo 'block rules loaded'\u001b[0m\r\n"]
-[11.650256, "o", "block rules loaded\r\n"]
-[12.05359, "o", "\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.2.20 | tail -3\u001b[0m\r\n"]
-[15.280329, "o", "\r\n--- 10.0.2.20 ping statistics ---\r\n2 packets transmitted, 0 packets received, 100% packet loss\r\n"]
-[15.683815, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -sr -vv | head -6\u001b[0m\r\n"]
-[15.98217, "o", "@0 block drop in quick inet proto icmp from any to 10.0.2.20\r\n  [ Evaluations: 3         Packets: 2         Bytes: 168         States: 0     ]\r\n  [ Inserted: uid 0 pid 1877 State Creations: 0     ]\r\n@1 pass in quick all flags S/SA\r\n  [ Evaluations: 1         Packets: 28        Bytes: 9296        States: 1     ]\r\n  [ Inserted: uid 0 pid 1877 State Creations: 1     ]\r\n"]
-[16.384573, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-pf.conf && echo 'back to the stateful ruleset'\u001b[0m\r\n"]
-[16.670067, "o", "back to the stateful ruleset\r\n"]
-[17.0729, "o", "\r\n\u001b[1m--- 7. NAT: the source is translated on the way out, restored on the way back ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# cat > /tmp/demo-nat.conf <<EOF\r\npass out quick on egress from 10.0.1.0/24 to any nat-to (eth2)\r\npass in quick on ingress proto icmp keep state\r\npass out quick on egress proto icmp keep state\r\nEOF\u001b[0m\r\n"]
-[17.740601, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-nat.conf && echo 'nat rules loaded'\u001b[0m\r\n"]
-[18.018113, "o", "nat rules loaded\r\n"]
-[18.42114, "o", "\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.2.20 | tail -3\u001b[0m\r\n"]
-[19.636475, "o", "--- 10.0.2.20 ping statistics ---\r\n2 packets transmitted, 2 packets received, 0% packet loss\r\nround-trip min/avg/max = 0.325/0.362/0.400 ms\r\n"]
-[20.038543, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -ss | grep -E 'icmp' | head -4\u001b[0m\r\n"]
-[20.310123, "o", "all icmp 10.0.2.20:8 <- 10.0.1.10:4999       0:0\r\nall icmp 10.0.2.1:7697 (10.0.1.10:4999) -> 10.0.2.20:8       0:0\r\n"]
-[20.712246, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-pf.conf && echo 'back to the stateful ruleset'\u001b[0m\r\n"]
-[20.990114, "o", "back to the stateful ruleset\r\n"]
-[21.392794, "o", "\r\n"]
-[21.393027, "o", "\u001b[1m--- 8. pflog: logged packets reach userspace (/dev/pflog) ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# cat > /tmp/demo-log.conf <<EOF\r\npass in quick log proto icmp from 10.0.1.10 keep state\r\npass out quick\r\nEOF\u001b[0m\r\n"]
-[22.057041, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-log.conf && echo 'log rule loaded'\u001b[0m\r\n"]
-[22.329918, "o", "log rule loaded\r\n"]
-[22.732644, "o", "\u001b[1;36mpftest-pf0# chmod +x /tmp/pflogd; rm -f /tmp/pflog.pcap; (setsid /tmp/pflogd -c 2 /tmp/pflog.pcap >/tmp/pflogd.log 2>&1 </dev/null &); sleep 1; echo 'pflogd collecting 2 records'\u001b[0m\r\n"]
-[23.981016, "o", "pflogd collecting 2 records\r\n"]
-[24.384736, "o", "\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.2.20 | tail -2\u001b[0m\r\n"]
-[25.612472, "o", "2 packets transmitted, 2 packets received, 0% packet loss\r\nround-trip min/avg/max = 0.356/0.429/0.502 ms\r\n"]
-[28.017578, "o", "\u001b[1;36mpftest-pf0# cat /tmp/pflogd.log; ls -l /tmp/pflog.pcap; echo 'pcap header (magic d4c3b2a1, linktype 0x75=DLT_PFLOG):'; od -An -tx1 -N24 /tmp/pflog.pcap\u001b[0m\r\n"]
-[28.277996, "o", "pflogd: 2 records\r\n-rw-------    1 root     root           352 Nov 12 01:06 /tmp/pflog.pcap\r\npcap header (magic d4c3b2a1, linktype 0x75=DLT_PFLOG):\r\n d4 c3 b2 a1 02 00 04 00 00 00 00 00 00 00 00 00\r\n ff ff 00 00 75 00 00 00\r\n"]
-[28.681267, "o", "\u001b[1;36mpftest-pf0# pkill pflogd 2>/dev/null; /opt/pf/pfctl -f /tmp/demo-pf.conf >/dev/null\u001b[0m\r\n"]
-[29.352889, "o", "\r\n\u001b[1m--- 9. divert-to: the packet goes to userspace and comes back ---\u001b[0m\r\n"]
-[29.35314, "o", "\u001b[1;36mpftest-pf0# cat /tmp/demo-divert.conf\u001b[0m\r\n"]
-[29.625878, "o", "pass in quick proto icmp from 10.0.1.10 to 10.0.1.1 divert-to \"10.0.1.1\" port 10000 keep state\r\npass out quick\r\n"]
-[30.028664, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-divert.conf && echo 'divert rule loaded'\u001b[0m\r\n"]
-[30.317998, "o", "divert rule loaded\r\n"]
-[30.719927, "o", "\u001b[1;36mpftest-pf0# chmod +x /tmp/pdivert; (setsid /tmp/pdivert -p 10000 -f >/tmp/pdivert.log 2>&1 </dev/null &); sleep 1; pgrep pdivert\u001b[0m\r\n"]
-[31.941535, "o", "1956\r\n"]
-[32.344, "o", "\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.1.1 | tail -3\u001b[0m\r\n"]
-[33.584192, "o", "--- 10.0.1.1 ping statistics ---\r\n2 packets transmitted, 2 packets received, 0% packet loss\r\nround-trip min/avg/max = 0.228/0.242/0.257 ms\r\n"]
-[33.987279, "o", "\u001b[1;36mpftest-pf0# head -3 /tmp/pdivert.log\u001b[0m\r\n"]
-[34.261872, "o", "pdivert: listening on divert port 10000\r\npdivert: got 84 bytes 10.0.1.10 -> 10.0.1.1\r\npdivert: got 84 bytes 10.0.1.10 -> 10.0.1.1\r\n"]
-[34.664226, "o", "  (pdivert flipped the last payload byte and fixed the ICMP checksum)\r\n\r\n"]
-[34.664382, "o", "\u001b[1m--- 10. shutdown ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# pkill pdivert; /opt/pf/pfctl -f /dev/null; /opt/pf/pfctl -d; echo 'pf disabled'\u001b[0m\r\n"]
-[34.938113, "o", "pf disabled\r\npf disabled\r\n"]
-[35.340577, "o", "\u001b[1;36mpftest-pf0# lsmod | grep '^pf '\u001b[0m\r\n"]
-[35.617928, "o", "pf                    552960  0\r\n"]
-[36.021187, "o", "\r\n\u001b[1mdemo over - port, gates and docs:\u001b[0m\r\n\u001b[1m  https://git.labexposed.com/lgcosta/pf-linux-port\u001b[0m\r\n\r\n"]
+{"version": 2, "width": 80, "height": 24, "timestamp": 1794449787, "env": {"SHELL": null, "TERM": "dumb"}}
+[1.414508, "o", "\u001b[1m===============================================================\u001b[0m\r\n\u001b[1m PF on Linux - the OpenBSD PF 8.0 engine inside the Linux kernel\u001b[0m\r\n\u001b[1m===============================================================\u001b[0m\r\n\r\nLab: 3 Alpine VMs under libvirt.\r\n  pftest-pf0 = firewall (kernel 7.3.4 built from source + pf.ko)\r\n  pftest-cli = client 10.0.1.10     pftest-srv = server 10.0.2.20\r\n\r\n\u001b[1m--- 1. our kernel, the OpenBSD engine as a module ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# uname -r\u001b[0m\r\n"]
+[1.655866, "o", "7.3.4\r\n"]
+[2.058621, "o", "\u001b[1;36mpftest-pf0# lsmod | grep '^pf ' || echo 'pf: not loaded yet'\u001b[0m\r\n"]
+[2.276696, "o", "pf: not loaded yet\r\n"]
+[2.680328, "o", "\u001b[1;36mpftest-pf0# insmod /opt/pf/pf.ko && dmesg | tail -3\u001b[0m\r\n"]
+[2.917691, "o", "[  146.252272] NET: Registered PF_IUCV protocol family\r\n[  146.252362] pfk: netfilter hooks registered (10, netisr wq data path)\r\n[  146.252423] pfk: PF-on-Linux engine loaded (OpenBSD 8.0 base)\r\n"]
+[3.320802, "o", "\r\n\u001b[1m--- 2. pfctl talks to the module over the OpenBSD ioctl ABI ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# /opt/pf/pfctl -s info | head -4\u001b[0m\r\n"]
+[3.598837, "o", "Status: Disabled for 0 days 00:02:26             Debug: err\r\n\r\nState Table                          Total             Rate\r\n  current entries                        0               \r\n"]
+[4.00249, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -e && /opt/pf/pfctl -s info | head -1\u001b[0m\r\n"]
+[4.274878, "o", "Status: Enabled                                  Debug: err\r\npf enabled\r\n"]
+[4.678074, "o", "\r\n\u001b[1m--- 3. a real pf.conf: tables, stateful rules, an explicit drop ---\u001b[0m\r\n"]
+[4.678128, "o", "\u001b[1;36mpftest-pf0# cat /tmp/demo-pf.conf\u001b[0m\r\n"]
+[4.954849, "o", "# PF-on-Linux demo ruleset (pf.conf syntax, real OpenBSD pfctl)\r\nset block-policy return\r\ntable <trusted> { 10.0.1.0/24 }\r\n\r\n# transit traffic: stateful, table-driven\r\npass in quick on ingress proto icmp from <trusted> keep state\r\npass out quick on egress proto icmp keep state\r\n\r\n# deny a specific destination\r\nblock drop in quick proto icmp to 10.0.9.99\r\n\r\n# everything else\r\npass in quick\r\npass out quick\r\n"]
+[5.358199, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-pf.conf && echo 'rules loaded'\u001b[0m\r\n"]
+[5.630704, "o", "rules loaded\r\n"]
+[6.034552, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -sr\u001b[0m\r\n"]
+[6.322794, "o", "pass in quick on ingress proto icmp from <trusted> to any\r\npass out quick on egress proto icmp all\r\nblock drop in quick inet proto icmp from any to 10.0.9.99\r\npass in quick all flags S/SA\r\npass out quick all flags S/SA\r\n"]
+[6.725786, "o", "\r\n"]
+[6.72584, "o", "\u001b[1m--- 4. transit traffic is allowed and stateful ---\u001b[0m\r\n\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.2.20 | tail -3\u001b[0m\r\n"]
+[7.977099, "o", "--- 10.0.2.20 ping statistics ---\r\n2 packets transmitted, 2 packets received, 0% packet loss\r\nround-trip min/avg/max = 0.339/0.351/0.363 ms\r\n"]
+[8.379918, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -ss | grep -E 'icmp' | head -4\u001b[0m\r\n"]
+[8.634572, "o", "all icmp 10.0.2.20:8 <- 10.0.1.10:5449       0:0\r\nall icmp 10.0.1.10:5449 -> 10.0.2.20:8       0:0\r\n"]
+[9.036709, "o", "\r\n\u001b[1m--- 5. tables are live objects ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# /opt/pf/pfctl -t trusted -T show\u001b[0m\r\n"]
+[9.298627, "o", "   10.0.1.0/24\r\n"]
+[9.701487, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -s Tables\u001b[0m\r\n"]
+[9.974937, "o", "trusted\r\n"]
+[10.378208, "o", "\r\n\u001b[1m--- 6. the drop rule actually drops ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# cat > /tmp/demo-block.conf <<EOF\r\nblock drop in quick proto icmp to 10.0.2.20\r\npass in quick\r\npass out quick\r\nEOF\u001b[0m\r\n"]
+[11.033956, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-block.conf && echo 'block rules loaded'\u001b[0m\r\n"]
+[11.310724, "o", "block rules loaded\r\n"]
+[11.714107, "o", "\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.2.20 | tail -3\u001b[0m\r\n"]
+[14.969152, "o", "\r\n--- 10.0.2.20 ping statistics ---\r\n2 packets transmitted, 0 packets received, 100% packet loss\r\n"]
+[15.372543, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -sr -vv | head -6\u001b[0m\r\n"]
+[15.66699, "o", "@0 block drop in quick inet proto icmp from any to 10.0.2.20\r\n  [ Evaluations: 6         Packets: 2         Bytes: 168         States: 0     ]\r\n  [ Inserted: uid 0 pid 1687 State Creations: 0     ]\r\n@1 pass in quick all flags S/SA\r\n  [ Evaluations: 1         Packets: 28        Bytes: 9296        States: 1     ]\r\n  [ Inserted: uid 0 pid 1687 State Creations: 1     ]\r\n"]
+[16.07016, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-pf.conf && echo 'back to the stateful ruleset'\u001b[0m\r\n"]
+[16.338781, "o", "back to the stateful ruleset\r\n"]
+[16.742479, "o", "\r\n\u001b[1m--- 7. NAT: the source is translated on the way out, restored on the way back ---\u001b[0m\r\n"]
+[16.742537, "o", "\u001b[1;36mpftest-pf0# cat > /tmp/demo-nat.conf <<EOF\r\npass out quick on egress from 10.0.1.0/24 to any nat-to (eth2)\r\npass in quick on ingress proto icmp keep state\r\npass out quick on egress proto icmp keep state\r\nEOF\u001b[0m\r\n"]
+[17.422636, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-nat.conf && echo 'nat rules loaded'\u001b[0m\r\n"]
+[17.686794, "o", "nat rules loaded\r\n"]
+[18.090339, "o", "\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.2.20 | tail -3\u001b[0m\r\n"]
+[19.341141, "o", "--- 10.0.2.20 ping statistics ---\r\n2 packets transmitted, 2 packets received, 0% packet loss\r\nround-trip min/avg/max = 0.276/0.317/0.359 ms\r\n"]
+[19.744749, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -ss | grep -E 'icmp' | head -4\u001b[0m\r\n"]
+[20.010971, "o", "all icmp 10.0.2.20:8 <- 10.0.1.10:5461       0:0\r\nall icmp 10.0.2.1:43040 (10.0.1.10:5461) -> 10.0.2.20:8       0:0\r\n"]
+[20.414328, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-pf.conf && echo 'back to the stateful ruleset'\u001b[0m\r\n"]
+[20.690817, "o", "back to the stateful ruleset\r\n"]
+[21.094035, "o", "\r\n\u001b[1m--- 8. pflog: logged packets reach userspace (/dev/pflog) ---\u001b[0m\r\n"]
+[21.094088, "o", "\u001b[1;36mpftest-pf0# cat > /tmp/demo-log.conf <<EOF\r\npass in quick log proto icmp from 10.0.1.10 keep state\r\npass out quick\r\nEOF\u001b[0m\r\n"]
+[21.762242, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-log.conf && echo 'log rule loaded'\u001b[0m\r\n"]
+[22.034943, "o", "log rule loaded\r\n"]
+[22.438523, "o", "\u001b[1;36mpftest-pf0# chmod +x /tmp/pflogd; rm -f /tmp/pflog.pcap; (setsid /tmp/pflogd -c 2 /tmp/pflog.pcap >/tmp/pflogd.log 2>&1 </dev/null &); sleep 1; echo 'pflogd collecting 2 records'\u001b[0m\r\n"]
+[23.681454, "o", "pflogd collecting 2 records\r\n"]
+[24.084864, "o", "\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.2.20 | tail -2\u001b[0m\r\n"]
+[25.333003, "o", "2 packets transmitted, 2 packets received, 0% packet loss\r\nround-trip min/avg/max = 0.352/0.364/0.376 ms\r\n"]
+[27.737616, "o", "\u001b[1;36mpftest-pf0# cat /tmp/pflogd.log; ls -l /tmp/pflog.pcap; echo 'pcap header (magic d4c3b2a1, linktype 0x75=DLT_PFLOG):'; od -An -tx1 -N24 /tmp/pflog.pcap\u001b[0m\r\n"]
+[28.026778, "o", "pflogd: 2 records\r\n-rw-------    1 root     root           324 Nov 12 02:16 /tmp/pflog.pcap\r\npcap header (magic d4c3b2a1, linktype 0x75=DLT_PFLOG):\r\n d4 c3 b2 a1 02 00 04 00 00 00 00 00 00 00 00 00\r\n ff ff 00 00 75 00 00 00\r\n"]
+[28.430241, "o", "\u001b[1;36mpftest-pf0# pkill pflogd 2>/dev/null; /opt/pf/pfctl -f /tmp/demo-pf.conf >/dev/null\u001b[0m\r\n"]
+[29.114632, "o", "\r\n\u001b[1m--- 9. route-to: force the next hop away from the normal path ---\u001b[0m\r\n"]
+[29.114687, "o", "\u001b[1;36mpftest-pf0# cat > /tmp/demo-route.conf <<EOF\r\npass in quick proto icmp from 10.0.1.10 to 10.0.2.20 route-to { 10.0.3.2 } keep state\r\npass out quick\r\nEOF\u001b[0m\r\n"]
+[29.778259, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-route.conf && echo 'route-to rule loaded'\u001b[0m\r\n"]
+[30.050898, "o", "route-to rule loaded\r\n"]
+[30.45427, "o", "\u001b[1;36mpftest-pf0# (tcpdump -ni eth3 -c 2 -e icmp > /tmp/route.td 2>&1 &); (tcpdump -ni eth2 -c 2 -e icmp > /tmp/norm.td 2>&1 &); sleep 1\u001b[0m\r\n"]
+[32.089063, "o", "\u001b[1;36mpftest-cli# ping -c1 -W2 10.0.2.20 | tail -2\u001b[0m\r\n"]
+[34.31667, "o", "--- 10.0.2.20 ping statistics ---\r\n1 packets transmitted, 0 packets received, 100% packet loss\r\n"]
+[36.72139, "o", "\u001b[1;36mpftest-pf0# echo 'forced egress (eth3, toward the gateway):'; grep -v '^tcpdump\\|^listening\\|^$' /tmp/route.td | head -2; echo 'normal egress (eth2):'; grep -c 'echo request' /tmp/norm.td\u001b[0m\r\n"]
+[37.006878, "o", "forced egress (eth3, toward the gateway):\r\n02:16:59.958272 52:54:00:aa:00:04 > 52:54:00:dd:00:02, ethertype IPv4 (0x0800), length 98: 10.0.1.10 > 10.0.2.20: ICMP echo request, id 5473, seq 0, length 64\r\nnormal egress (eth2):\r\n0\r\n"]
+[37.410476, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-pf.conf >/dev/null\u001b[0m\r\n"]
+[38.094888, "o", "\r\n\u001b[1m--- 10. divert-to: the packet goes to userspace and comes back ---\u001b[0m\r\n"]
+[38.095122, "o", "\u001b[1;36mpftest-pf0# cat /tmp/demo-divert.conf\u001b[0m\r\n"]
+[38.35866, "o", "pass in quick proto icmp from 10.0.1.10 to 10.0.1.1 divert-to \"10.0.1.1\" port 10000 keep state\r\npass out quick\r\n"]
+[38.763007, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-divert.conf && echo 'divert rule loaded'\u001b[0m\r\n"]
+[39.022814, "o", "divert rule loaded\r\n"]
+[39.42606, "o", "\u001b[1;36mpftest-pf0# chmod +x /tmp/pdivert; (setsid /tmp/pdivert -p 10000 -f >/tmp/pdivert.log 2>&1 </dev/null &); sleep 1; pgrep pdivert\u001b[0m\r\n"]
+[40.654519, "o", "1794\r\n"]
+[41.056785, "o", "\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.1.1 | tail -3\u001b[0m\r\n"]
+[42.284778, "o", "--- 10.0.1.1 ping statistics ---\r\n2 packets transmitted, 2 packets received, 0% packet loss\r\nround-trip min/avg/max = 0.177/0.224/0.271 ms\r\n"]
+[42.691426, "o", "\u001b[1;36mpftest-pf0# head -3 /tmp/pdivert.log\u001b[0m\r\n"]
+[42.942601, "o", "pdivert: listening on divert port 10000\r\npdivert: got 84 bytes 10.0.1.10 -> 10.0.1.1\r\npdivert: got 84 bytes 10.0.1.10 -> 10.0.1.1\r\n"]
+[43.344696, "o", "  (pdivert flipped the last payload byte and fixed the ICMP checksum)\r\n\r\n\u001b[1m--- 11. shutdown ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# pkill pdivert; /opt/pf/pfctl -f /dev/null; /opt/pf/pfctl -d; echo 'pf disabled'\u001b[0m\r\n"]
+[43.626606, "o", "pf disabled\r\npf disabled\r\n"]
+[44.028882, "o", "\u001b[1;36mpftest-pf0# lsmod | grep '^pf '\u001b[0m\r\n"]
+[44.286597, "o", "pf                    552960  0\r\n"]
+[44.688511, "o", "\r\n\u001b[1mdemo over - port, gates and docs:\u001b[0m\r\n\u001b[1m  https://git.labexposed.com/lgcosta/pf-linux-port\u001b[0m\r\n"]
+[44.688631, "o", "\r\n"]

scripts/demo-session.sh

@@ -151,7 +151,20 @@ p0 "cat /tmp/pflogd.log; ls -l /tmp/pflog.pcap; echo 'pcap header (magic d4c3b2a
 p0 "pkill pflogd 2>/dev/null; /opt/pf/pfctl -f /tmp/demo-pf.conf >/dev/null"
 echo
 
-bold "--- 9. divert-to: the packet goes to userspace and comes back ---"
+bold "--- 9. route-to: force the next hop away from the normal path ---"
+p0 "cat > /tmp/demo-route.conf <<EOF
+pass in quick proto icmp from $CLI_IP to $SRV_IP route-to { 10.0.3.2 } keep state
+pass out quick
+EOF"
+p0 "/opt/pf/pfctl -f /tmp/demo-route.conf && echo 'route-to rule loaded'"
+p0 "(tcpdump -ni eth3 -c 2 -e icmp > /tmp/route.td 2>&1 &); (tcpdump -ni eth2 -c 2 -e icmp > /tmp/norm.td 2>&1 &); sleep 1"
+vmc "ping -c1 -W2 $SRV_IP | tail -2"
+sleep 2
+p0 "echo 'forced egress (eth3, toward the gateway):'; grep -v '^tcpdump\|^listening\|^$' /tmp/route.td | head -2; echo 'normal egress (eth2):'; grep -c 'echo request' /tmp/norm.td"
+p0 "/opt/pf/pfctl -f /tmp/demo-pf.conf >/dev/null"
+echo
+
+bold "--- 10. divert-to: the packet goes to userspace and comes back ---"
 p0 "cat /tmp/demo-divert.conf"
 p0 "/opt/pf/pfctl -f /tmp/demo-divert.conf && echo 'divert rule loaded'"
 p0 "chmod +x /tmp/pdivert; (setsid /tmp/pdivert -p 10000 -f >/tmp/pdivert.log 2>&1 </dev/null &); sleep 1; pgrep pdivert"
@@ -160,7 +173,7 @@ p0 "head -3 /tmp/pdivert.log"
 echo "  (pdivert flipped the last payload byte and fixed the ICMP checksum)"
 echo
 
-bold "--- 10. shutdown ---"
+bold "--- 11. shutdown ---"
 p0 "pkill pdivert; /opt/pf/pfctl -f /dev/null; /opt/pf/pfctl -d; echo 'pf disabled'"
 p0 "lsmod | grep '^pf '"
 echo

tests/vm/07-binat.sh

@@ -0,0 +1,48 @@
+#!/usr/bin/env bash
+# M3 gate: binat-to — bidirectional (static 1:1) NAT.
+#
+# Lab: the server (10.0.2.20) pings the client (10.0.1.10) through pf0.  The
+# binat rule rewrites the source to 10.0.2.50; the client's reply goes back to
+# 10.0.2.50, which pf0 owns in the mapping, and is translated to the server.
+#
+# Proves: outbound source rewrite + inbound destination rewrite with one rule,
+# and that the reply survives the state/translation path.
+set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
+
+BINAT=10.0.2.50
+
+pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
+pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
+
+cat > /tmp/g07.conf <<C
+pass quick proto icmp from $SRV_IP to $CLI_IP binat-to $BINAT keep state
+pass in quick proto icmp keep state
+pass out quick proto icmp keep state
+C
+pfload /tmp/g07.conf || { bad "binat rule load"; finish; }
+# pfctl expands one binat-to rule into the documented pair:
+#   pass out ... nat-to <mapped> static-port   (outbound half)
+#   pass in  ... rdr-to <real>                 (inbound half)
+RULES=$(pf0 '/opt/pf/pfctl -sr')
+echo "$RULES" | grep -q "nat-to $BINAT static-port" && ok "binat outbound half installed" || bad "outbound half missing"
+echo "$RULES" | grep -q "rdr-to $SRV_IP" && ok "binat inbound half installed" || bad "inbound half missing"
+
+# capture on the client side (resolve its transit interface, like pf0's)
+CLI_DEV=$(cli "ip route get $SRV_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
+[ -n "$CLI_DEV" ] || CLI_DEV=eth1
+cli "(tcpdump -ni $CLI_DEV -c 4 -e icmp > /tmp/bi.td 2>&1 &)" 2>/dev/null
+sleep 1
+srv "ping -c2 -W2 $CLI_IP >/dev/null 2>&1" && ok "ping srv->cli through binat" || bad "binat round trip"
+sleep 2
+
+TD=$(cli 'cat /tmp/bi.td' 2>/dev/null)
+if echo "$TD" | grep -q "$BINAT"; then
+	ok "request arrived from the mapped address $BINAT"
+else
+	bad "mapped address not seen on the client: $(echo "$TD" | head -2)"
+fi
+echo "$TD" | grep -q "$SRV_IP" && bad "original address $SRV_IP leaked" || ok "original source not leaked"
+
+pf0 '/opt/pf/pfctl -ss' | grep -q "$BINAT" && ok "state shows the mapping" || bad "no binat state"
+pf0 '/opt/pf/pfctl -d' >/dev/null
+finish

tests/vm/08-routeto.sh

@@ -0,0 +1,67 @@
+#!/usr/bin/env bash
+# M4 gate: route-to / dup-to — forced forwarding path (pf_route).
+#
+# The lab's host bridge filters *forwarded* frames that cross two libvirt
+# networks with a foreign source address, so the proof is taken on the
+# firewall itself: which of pf0's egress interfaces the packet leaves from.
+#
+#   route-to { gw2 }  -> packet leaves via eth3 (toward gw2), NOT via eth2
+#   dup-to  { gw2 }   -> packet leaves via eth2 (normal path) AND a copy on eth3
+set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
+
+pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
+pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
+
+# resolve pf0's interfaces by address (names are stable, but be safe)
+IF_SRV=$(pf0 "ip route get $SRV_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
+IF_GW=$(pf0 "ip route get $GW2_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
+[ -n "$IF_SRV" ] && [ -n "$IF_GW" ] || { bad "interface resolution"; finish; }
+[ "$IF_SRV" != "$IF_GW" ] || { bad "transit and gateway share an interface"; finish; }
+ok "normal egress=$IF_SRV  forced egress=$IF_GW"
+
+
+# count matching lines on pf0, robust against a missing/empty capture file
+# (grep exits 1 on zero matches, and the ssh wrapper hides stderr)
+cnt() {
+	local f=$1 pat=$2 n
+	n=$(pf0 "grep -c -- '$pat' $f 2>/dev/null; true" | tr -dc '0-9')
+	[ -n "$n" ] || n=0
+	printf '%s' "$n"
+}
+
+# capture both egresses at once
+start_captures() {
+	pf0 "pkill tcpdump; (tcpdump -ni $IF_SRV -c 6 -e icmp > /tmp/srv.td 2>&1 &); (tcpdump -ni $IF_GW -c 6 -e icmp > /tmp/gw.td 2>&1 &); sleep 1" >/dev/null
+}
+
+cat > /tmp/g08a.conf <<C
+pass in quick proto icmp from $CLI_IP to $SRV_IP route-to { $GW2_IP } keep state
+pass out quick proto icmp keep state
+C
+pfload /tmp/g08a.conf || { bad "route-to rule load"; finish; }
+pf0 '/opt/pf/pfctl -sr' | grep -q 'route-to' && ok "route-to rule listed" || bad "route-to not listed"
+start_captures
+cli "ping -c2 -W2 $SRV_IP >/dev/null 2>&1"
+sleep 2
+# count only echo *requests* from the client (a reply also contains its address)
+N=$(cnt /tmp/gw.td "$CLI_IP > $SRV_IP"); [ "$N" -gt 0 ] && ok "route-to: packet left via $IF_GW ($N)" \
+	|| bad "route-to: nothing on $IF_GW"
+N=$(cnt /tmp/srv.td "$CLI_IP > $SRV_IP"); [ "$N" -eq 0 ] && ok "route-to: normal egress $IF_SRV not used" \
+	|| bad "route-to: $N requests also left via $IF_SRV"
+
+cat > /tmp/g08b.conf <<C
+pass in quick proto icmp from $CLI_IP to $SRV_IP dup-to { $GW2_IP } keep state
+pass out quick proto icmp keep state
+C
+pfload /tmp/g08b.conf || { bad "dup-to rule load"; finish; }
+pf0 '/opt/pf/pfctl -sr' | grep -q 'dup-to' && ok "dup-to rule listed" || bad "dup-to not listed"
+start_captures
+cli "ping -c2 -W2 $SRV_IP >/dev/null 2>&1"
+sleep 2
+N=$(cnt /tmp/srv.td "$CLI_IP > $SRV_IP"); [ "$N" -gt 0 ] && ok "dup-to: original path kept ($N on $IF_SRV)" \
+	|| bad "dup-to: original path lost"
+N=$(cnt /tmp/gw.td "$CLI_IP > $SRV_IP"); [ "$N" -gt 0 ] && ok "dup-to: duplicate sent to $IF_GW ($N)" \
+	|| bad "dup-to: no duplicate"
+
+pf0 'pkill tcpdump; /opt/pf/pfctl -d' >/dev/null
+finish

tests/vm/09-scrub.sh

@@ -0,0 +1,54 @@
+#!/usr/bin/env bash
+# M3 gate: scrub - normalization actually rewrites packets.
+#
+# 8.0 syntax: scrub is a rule option ("match in all scrub (...)"), not a
+# standalone rule.  Proof is taken on pf0's own egress (the lab's host bridge
+# filters forwarded frames between networks, so peer-side captures are not
+# reliable):
+#   min-ttl 100   -> a transit packet with ttl 64 leaves with ttl 100
+#   max-mss 500   -> a TCP SYN with MSS 1460 leaves advertising MSS 500
+set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
+
+pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
+pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
+
+IF_SRV=$(pf0 "ip route get $SRV_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
+[ -n "$IF_SRV" ] || IF_SRV=eth2
+
+cat > /tmp/g09.conf <<C
+set reassemble yes
+match in all scrub (min-ttl 100 max-mss 500)
+pass in quick proto icmp from $CLI_IP keep state
+pass in quick proto tcp from $CLI_IP to $SRV_IP port 9092 keep state
+pass out quick keep state
+C
+pfload /tmp/g09.conf || { bad "scrub rules load"; finish; }
+pf0 '/opt/pf/pfctl -sr' | grep -q 'scrub' && ok "scrub rule listed" || bad "scrub not listed"
+
+# --- min-ttl on a transit ICMP packet ---
+# OpenBSD raises the TTL to min-ttl in pf, then ip_forward() decrements it for
+# the hop, so the egress packet shows min-ttl-1 (100 -> 99).
+pf0 "pkill tcpdump; (tcpdump -ni $IF_SRV -c 3 -vv icmp > /tmp/scr1.td 2>&1 &); sleep 1"
+cli "ping -c2 -W2 $SRV_IP >/dev/null 2>&1"
+sleep 2
+N=$(pf0 "grep -c 'ttl 99' /tmp/scr1.td 2>/dev/null; true" | tr -dc '0-9')
+if [ "${N:-0}" -gt 0 ]; then
+	ok "min-ttl applied (ttl raised to 100, forwarded as 99)"
+else
+	DIAG=$(pf0 "grep -o 'ttl [0-9]*' /tmp/scr1.td 2>/dev/null | head -2" | tr '\n' ' ')
+	bad "min-ttl not applied: $DIAG"
+fi
+
+# --- max-mss on a TCP SYN ---
+pf0 "(tcpdump -ni $IF_SRV -c 3 -vv tcp port 9092 > /tmp/scr2.td 2>&1 &); sleep 1"
+cli "nc -w1 -z $SRV_IP 9092 >/dev/null 2>&1"
+sleep 2
+if pf0 "grep -q 'mss 500' /tmp/scr2.td" 2>/dev/null; then
+	ok "max-mss clamped to 500"
+else
+	DIAG=$(pf0 "grep -o 'mss [0-9]*' /tmp/scr2.td 2>/dev/null | head -2" | tr '\n' ' ')
+	bad "mss not clamped: $DIAG"
+fi
+
+pf0 'pkill tcpdump; /opt/pf/pfctl -d' >/dev/null
+finish

tests/vm/10-pools.sh

@@ -0,0 +1,68 @@
+#!/usr/bin/env bash
+# M4 gate: route-to pools - round-robin vs source-hash (pf_lb).
+#
+# Two gateways live on two different firewall links:
+#   10.0.3.2 via $IF_GW   (gw2's 10.0.3 side)
+#   10.0.2.2 via $IF_SRV  (gw2's 10.0.2 side)
+# Each ping is a separate flow (own state), so the pool choice is made per
+# flow: round-robin must spread the flows over both links, source-hash must
+# keep them on one (same source address -> same bucket).
+set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
+
+GW1=$GW2_IP			# 10.0.3.2
+GW2=10.0.2.2
+
+pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
+pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
+
+IF_GW=$(pf0 "ip route get $GW1 | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
+IF_SRV=$(pf0 "ip route get $SRV_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
+[ -n "$IF_GW" ] && [ -n "$IF_SRV" ] || { bad "interface resolution"; finish; }
+[ "$IF_GW" != "$IF_SRV" ] || { bad "the two gateways share a link"; finish; }
+ok "pool links: $IF_GW ($GW1) and $IF_SRV ($GW2)"
+
+count_on() {	# count echo requests captured on an interface
+	local n
+	n=$(pf0 "grep -c '$CLI_IP > $SRV_IP' /tmp/pool_$1.td 2>/dev/null; true" | tr -dc '0-9')
+	[ -n "$n" ] || n=0
+	printf '%s' "$n"
+}
+
+run_flows() {	# $1 = ruleset file, four separate ICMP flows
+	pf0 "pkill tcpdump; (tcpdump -ni $IF_GW -c 8 -e icmp > /tmp/pool_gw.td 2>&1 &); (tcpdump -ni $IF_SRV -c 8 -e icmp > /tmp/pool_srv.td 2>&1 &); sleep 1" >/dev/null
+	cli "for i in 1 2 3 4; do ping -c1 -W2 $SRV_IP >/dev/null 2>&1; done"
+	sleep 2
+}
+
+# --- round-robin: the flows must spread over both links ---
+cat > /tmp/g10a.conf <<C
+pass in quick proto icmp from $CLI_IP to $SRV_IP route-to { $GW1, $GW2 } round-robin keep state
+pass out quick keep state
+C
+pfload /tmp/g10a.conf || { bad "rr rule load"; finish; }
+run_flows
+A=$(count_on gw); B=$(count_on srv)
+# Captures are lossy under busybox tcpdump, so the assertions are about
+# *which links are used*, not how many packets arrived.
+if [ "$A" -gt 0 ] && [ "$B" -gt 0 ]; then
+	ok "round-robin used both links ($A on $IF_GW, $B on $IF_SRV)"
+else
+	bad "round-robin did not spread ($A on $IF_GW, $B on $IF_SRV)"
+fi
+
+# --- source-hash: the same source sticks to one gateway ---
+cat > /tmp/g10b.conf <<C
+pass in quick proto icmp from $CLI_IP to $SRV_IP route-to { $GW1, $GW2 } source-hash keep state
+pass out quick keep state
+C
+pfload /tmp/g10b.conf || { bad "source-hash rule load"; finish; }
+run_flows
+A=$(count_on gw); B=$(count_on srv)
+if [ "$((A + B))" -ge 1 ] && { [ "$A" -eq 0 ] || [ "$B" -eq 0 ]; }; then
+	ok "source-hash pinned the flows to one link ($A on $IF_GW, $B on $IF_SRV)"
+else
+	bad "source-hash spread the flows ($A on $IF_GW, $B on $IF_SRV)"
+fi
+
+pf0 'pkill tcpdump; /opt/pf/pfctl -d' >/dev/null
+finish

tests/vm/13-replyto.sh

@@ -0,0 +1,52 @@
+#!/usr/bin/env bash
+# M4 gate: reply-to - force the next hop of the *reply* direction.
+#
+# reply-to is the asymmetric-routing tool: a flow whose request arrives on one
+# link can have its answer pushed out through a different gateway.  Proof is
+# taken on pf0's own interfaces (the lab's host bridge filters forwarded frames
+# that cross networks, so the peer side is not observable):
+#
+#   request  cli -> srv   leaves via $IF_SRV (normal path, untouched)
+#   reply    srv -> cli   leaves via $IF_GW  (forced by reply-to), not $IF_CLI
+set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
+
+pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
+pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
+
+IF_SRV=$(pf0 "ip route get $SRV_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
+IF_GW=$(pf0 "ip route get $GW2_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
+IF_CLI=$(pf0 "ip route get $CLI_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
+[ -n "$IF_SRV" ] && [ -n "$IF_GW" ] && [ -n "$IF_CLI" ] || { bad "interface resolution"; finish; }
+[ "$IF_GW" != "$IF_CLI" ] || { bad "gateway and client share a link"; finish; }
+ok "reply would normally leave via $IF_CLI, forced via $IF_GW"
+
+cat > /tmp/g13.conf <<C
+pass in quick proto icmp from $CLI_IP to $SRV_IP reply-to { $GW2_IP } keep state
+pass out quick keep state
+C
+pfload /tmp/g13.conf || { bad "reply-to rule load"; finish; }
+pf0 '/opt/pf/pfctl -sr' | grep -q 'reply-to' && ok "reply-to rule listed" || bad "reply-to not listed"
+
+pf0 "pkill tcpdump; (tcpdump -ni $IF_GW -c 8 -e icmp > /tmp/rt_gw.td 2>&1 &); (tcpdump -ni $IF_CLI -c 8 -e icmp > /tmp/rt_cli.td 2>&1 &); (tcpdump -ni $IF_SRV -c 8 -e icmp > /tmp/rt_srv.td 2>&1 &); sleep 1" >/dev/null
+cli "ping -c2 -W2 $SRV_IP >/dev/null 2>&1"
+sleep 2
+
+cnt() {
+	local n
+	n=$(pf0 "grep -c -- '$2' /tmp/rt_$1.td 2>/dev/null; true" | tr -dc '0-9')
+	[ -n "$n" ] || n=0
+	printf '%s' "$n"
+}
+
+# the request path must be unchanged
+N=$(cnt srv "$CLI_IP > $SRV_IP"); [ "$N" -gt 0 ] && ok "request left via $IF_SRV ($N)" \
+	|| bad "request did not leave via $IF_SRV"
+
+# the reply must be forced to the gateway link
+N=$(cnt gw "$SRV_IP > $CLI_IP"); [ "$N" -gt 0 ] && ok "reply forced onto $IF_GW ($N)" \
+	|| bad "reply not seen on $IF_GW"
+N=$(cnt cli "$SRV_IP > $CLI_IP"); [ "$N" -eq 0 ] && ok "reply did not use $IF_CLI" \
+	|| bad "reply still left via $IF_CLI ($N)"
+
+pf0 'pkill tcpdump; /opt/pf/pfctl -d' >/dev/null
+finish

tests/vm/15-queue.sh

@@ -0,0 +1,68 @@
+#!/usr/bin/env bash
+# M5 gate: hfsc queue in the data path.
+#
+# What is verifiable with OpenBSD 8.0's pf: a queue configuration loads, the
+# hfsc discipline attaches to the interface, `pfctl -s queue -v` reports the
+# class statistics, a queued flow completes through the class, and that class's
+# packet/byte counters advance - i.e. the scheduler really sits in the path.
+#
+# What is NOT a cap here: 8.0's pf.conf exposes only `bandwidth` (HFSC
+# linkshare).  There is no `minimum`/`maximum` keyword in this vintage, and
+# linkshare is a guarantee under contention, not a limit on a lone flow - the
+# same on OpenBSD.  Timing is printed for information, not asserted.
+set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
+
+SZ=2000000
+IF_GW=$(pf0 "ip route get $SRV_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
+[ -n "$IF_GW" ] || IF_GW=eth2
+
+pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
+pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
+
+cat > /tmp/g15.conf <<C
+queue rootq on $IF_GW bandwidth 10Mbit
+queue leafq on $IF_GW bandwidth 2Mbit parent rootq default
+pass in quick proto tcp from $CLI_IP to $SRV_IP port 9095 queue leafq keep state
+pass out quick keep state
+C
+pfload /tmp/g15.conf || { bad "queue rules load"; finish; }
+
+# 1) both classes are visible with statistics
+Q=$(pf0 '/opt/pf/pfctl -s queue -v')
+if echo "$Q" | grep -q 'rootq' && echo "$Q" | grep -q 'leafq'; then
+	ok "pfctl -s queue lists both classes"
+else
+	bad "queue stats missing: $(echo "$Q" | head -2)"
+fi
+
+# 2) a queued flow completes
+srv "pkill nc 2>/dev/null; head -c $SZ /dev/zero | tr '\\0' A > /tmp/pa.bin; sleep 1; (setsid nc -l -p 9095 < /tmp/pa.bin >/dev/null 2>&1 &); sleep 1" >/dev/null
+T0=$(date +%s%N)
+GOT=$(cli "nc -w60 10.0.2.20 9095 > /tmp/oa.bin; wc -c < /tmp/oa.bin" | tr -d '[:space:]')
+T1=$(date +%s%N)
+if [ "${GOT:-0}" -ge "$SZ" ]; then
+	ok "queued flow completed ($GOT bytes in $(( (T1-T0)/1000000 )) ms)"
+else
+	bad "queued flow incomplete (got $GOT of $SZ)"
+	finish
+fi
+
+# 3) the scheduler actually counted the class
+sleep 1
+Q2=$(pf0 '/opt/pf/pfctl -s queue -v')
+# line after the leafq header looks like:  [ pkts:   37  bytes:  1932  dropped ...
+LEAF_PKTS=$(printf '%s\n' "$Q2" | grep -A1 'leafq' | tail -1 |
+	sed -n 's/^[[:space:]]*\[[[:space:]]*pkts:[[:space:]]*\([0-9][0-9]*\).*/\1/p')
+if [ -n "$LEAF_PKTS" ] && [ "$LEAF_PKTS" -gt 0 ] 2>/dev/null; then
+	ok "hfsc class counted traffic (leafq pkts=$LEAF_PKTS)"
+else
+	bad "hfsc class counters did not move: $(printf '%s\n' "$Q2" | grep -A1 leafq | tail -1)"
+fi
+
+# 4) the firewall is still healthy after queueing
+pf0 'echo SSH_ALIVE' | grep -q SSH_ALIVE && ok "firewall responsive after queued transfer" \
+	|| bad "firewall unresponsive after queueing"
+
+pf0 '/opt/pf/pfctl -d' >/dev/null
+srv 'pkill nc 2>/dev/null; true' >/dev/null
+finish